© 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. 114830
    Prev
    Next
    INDEX
    Explanations

    first inaugural

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

    understanding optional insufficient integrated failing artifacts needs

    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
    Խ
    0.50
    ின்ற
    0.46
    EXPL
    0.43
    ктором
    0.42
    Ley
    0.42
        
    0.41
     transm
    0.41
    لاميذ
    0.40
    RoundRect
    0.40
    SpriteCollision
    0.40
    POSITIVE LOGITS
    蹒
    0.47
     উঠে
    0.46
     ۲۰۰
    0.46
     slits
    0.45
     सॉ
    0.43
    一套
    0.43
     সর্বোচ্চ
    0.42
    ায়ার
    0.42
     bonuses
    0.42
    靴
    0.42
    Activations Density 0.001%

    No Known Activations