© 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. 162672
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

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

    age + children + sexualization

    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
    ف
    0.43
    <h3>
    0.43
    <h2>
    0.41
    <h5>
    0.41
    カスタ
    0.41
    オ
    0.41
    ली
    0.40
    制
    0.40
     refinance
    0.39
    прода
    0.39
    POSITIVE LOGITS
     assayed
    0.46
     basiert
    0.46
     fuer
    0.45
     perfused
    0.44
    getPopulation
    0.43
     জন্য
    0.43
     algebras
    0.42
     Bcl
    0.42
     এখানকার
    0.41
     teorema
    0.41
    Activations Density 0.000%

    No Known Activations