© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13723
    Prev
    Next
    INDEX
    Explanations

    names after contrast words

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

    names following commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     】
    0.42
     -
    0.40
    】
    0.40
    、
    0.40
    »
    0.38
    （
    0.38
     <*>
    0.37
     (%)
    0.37
    三
    0.37
    °
    0.36
    POSITIVE LOGITS
     tačiau
    0.55
     tuttavia
    0.48
     però
    0.45
     ironically
    0.42
    however
    0.41
     however
    0.41
     lakini
    0.40
     dutiful
    0.39
     aptly
    0.39
     însă
    0.38
    Activations Density 0.046%

    No Known Activations