© 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. 73260
    Prev
    Next
    INDEX
    Explanations

    comment formgallery below

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

    Acceptance Criteria

    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
    кую
    0.52
     δυνατό
    0.50
     fonctionner
    0.47
    金
    0.46
     стан
    0.46
     यंदा
    0.46
     στά
    0.46
    𝚔
    0.45
     prov
    0.45
     பிரதமர்
    0.45
    POSITIVE LOGITS
    Yon
    0.47
    মোহনের
    0.44
    μου
    0.43
    Noeud
    0.42
     PW
    0.41
     prejudiced
    0.41
    .",
    0.41
    0.41
     Saunders
    0.41
     Yon
    0.41
    Activations Density 0.003%

    No Known Activations