© 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. 15149
    Prev
    Next
    INDEX
    Explanations

    non refundable

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

    non-consensual

    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
     странице
    0.60
     commentaires
    0.59
     oldCount
    0.59
     MANY
    0.58
     `:`,
    0.58
     způ
    0.57
     Seite
    0.57
     pouces
    0.55
     İlk
    0.55
     Vikipedi
    0.55
    POSITIVE LOGITS
     non
    1.17
    non
    0.96
     Non
    0.91
     नॉन
    0.90
    非
    0.86
    NON
    0.85
    Non
    0.80
     NON
    0.76
     非
    0.76
    -
    0.76
    Activations Density 0.036%

    No Known Activations