© 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. 148079
    Prev
    Next
    INDEX
    Explanations

    regional representative

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

    imagination or already noticing

    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
    Tools
    0.44
    tools
    0.41
    ظ
    0.40
    asjon
    0.40
     tools
    0.39
    ipelago
    0.39
    itesse
    0.39
    ST
    0.38
    menos
    0.38
    fica
    0.38
    POSITIVE LOGITS
     ใ
    0.49
    AnimationStyle
    0.47
     оттен
    0.47
     店舗
    0.47
     atmosfer
    0.47
    ৩৯
    0.46
     いや
    0.46
     архівної
    0.46
    芢
    0.46
    তাহাকে
    0.45
    Activations Density 0.001%

    No Known Activations