© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14181
    Prev
    Next
    INDEX
    Explanations

    well followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     overarching
    -3.47
    皲
    -3.39
     delightfully
    -3.38
     andere
    -3.38
    驺
    -3.33
     quintessential
    -3.25
     dando
    -3.23
     relentless
    -3.22
     immense
    -3.14
     quatre
    -3.13
    POSITIVE LOGITS
    There
    4.03
    That
    3.98
    With
    3.97
    When
    3.97
    While
    3.69
    This
    3.69
    Almost
    3.64
    Those
    3.61
     With
    3.59
    Even
    3.58
    Activations Density 0.059%

    No Known Activations