© 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. 47928
    Prev
    Next
    INDEX
    Explanations

    Star Wars characters and places

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

    algebraic expressions and equations

    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
     Bewer
    0.45
    聁
    0.42
    commonByteArray
    0.41
    夾
    0.40
    ᵑ
    0.40
     Huh
    0.39
    বৃষ্টি
    0.39
    再加上
    0.39
    㽚
    0.39
    窣
    0.38
    POSITIVE LOGITS
     дека
    0.41
    CA
    0.40
    e
    0.40
    숍
    0.40
    Europe
    0.39
     instalments
    0.39
    april
    0.38
    TAB
    0.38
    ppermint
    0.38
    April
    0.37
    Activations Density 0.001%

    No Known Activations