© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20849
    Prev
    Next
    INDEX
    Explanations

    Immunotoxins

    np_acts-logits-general · gemini-2.5-flash-lite

    CSS class definitions for form elements, particularly "form-" prefixed classes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on the Bootstrap “form-group” class in HTML forms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -2.09
     '-
    -2.05
    ',
    -1.89
    ,'
    -1.85
     manifestó
    -1.84
     ('
    -1.66
    ('
    -1.66
     sostuvo
    -1.66
     '.
    -1.64
     advirtió
    -1.62
    POSITIVE LOGITS
    <bos>
    1.67
     of
    1.64
     other
    1.49
     alumn
    1.42
     moter
    1.38
     autob
    1.37
    酲
    1.33
     galleria
    1.32
     lazer
    1.31
     pama
    1.28
    Activations Density 0.002%

    No Known Activations