© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112200
    Prev
    Next
    INDEX
    Explanations

    digital wallet or REM sleep disorder

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

    iPhone, portfolio, landlords

    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
     yoki
    0.50
    पर्यंत
    0.50
     kuasa
    0.48
    ㅀ
    0.47
    ruk
    0.47
    voren
    0.47
    elernt
    0.46
     없
    0.45
    denes
    0.44
    癮
    0.44
    POSITIVE LOGITS
     আঙ্গ
    0.47
    Productions
    0.46
     অর্থে
    0.43
     কর্মকাণ্ড
    0.43
     アウトドア
    0.43
     softmax
    0.43
     ഭാഗ
    0.42
    িত্তিক
    0.42
     オリ
    0.42
     closets
    0.41
    Activations Density 0.000%

    No Known Activations