© 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. 40724
    Prev
    Next
    INDEX
    Explanations

    verb phrases followed by nouns

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

    extra features or turns

    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
     dür
    0.51
     forbid
    0.48
     incorporar
    0.46
    錤
    0.46
     reprint
    0.45
     throwIf
    0.43
     禁止
    0.43
    owała
    0.42
     wont
    0.42
     prohibits
    0.42
    POSITIVE LOGITS
    righteous
    0.53
     दिव
    0.50
    ▥
    0.48
    TAN
    0.48
    Suy
    0.46
    🇲
    0.46
     देण्यासाठी
    0.45
    DS
    0.44
     پلی
    0.44
     Walking
    0.44
    Activations Density 0.000%

    No Known Activations