© 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. 162536
    Prev
    Next
    INDEX
    Explanations

    causal conjunction or explanation

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

    private companies

    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
    POSITORY
    0.43
    宅配
    0.43
    認為
    0.42
    acteria
    0.42
     Barnard
    0.41
    察
    0.41
     arke
    0.41
    著
    0.41
     dizer
    0.41
    賊
    0.41
    POSITIVE LOGITS
     fuc
    0.42
     تتم
    0.42
     或
    0.41
     spells
    0.41
     _____
    0.41
     millennia
    0.41
    ادس
    0.40
     بُ
    0.40
     হ্রাস
    0.40
     Loire
    0.39
    Activations Density 0.001%

    No Known Activations