© 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. 158152
    Prev
    Next
    INDEX
    Explanations

    following certain words

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

    understood platforms

    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
    nik
    0.54
    never
    0.52
    st
    0.52
    0.51
    so
    0.48
    no
    0.47
    kov
    0.47
    a
    0.47
    regular
    0.47
    I
    0.47
    POSITIVE LOGITS
    を利用
    0.51
     ступен
    0.50
     곳
    0.48
     ይችላሉ
    0.46
     дает
    0.46
    优秀的
    0.46
     ಬಂದ
    0.45
     cattle
    0.44
    发生的
    0.44
    াপন্ন
    0.44
    Activations Density 0.001%

    No Known Activations