© 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. 163654
    Prev
    Next
    INDEX
    Explanations

    linking to or endorsing websites

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

    legal compliance, Spanish, cocktail named

    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
     மட்டு
    0.48
     slumber
    0.47
    ました
    0.45
    bedingt
    0.44
    stelling
    0.44
     மட்டுமல்ல
    0.44
     மிகப்
    0.44
    𝐰
    0.43
     ଚ
    0.43
    lijk
    0.43
    POSITIVE LOGITS
     armas
    0.44
     hered
    0.44
    صی
    0.43
    alassemia
    0.43
     derivadas
    0.42
    অভি
    0.42
     অভিযোগে
    0.41
    می
    0.41
    Subview
    0.41
     cpf
    0.40
    Activations Density 0.000%

    No Known Activations