© 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. 106532
    Prev
    Next
    INDEX
    Explanations

    scale mining

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

    identifying antigens, CPU architecture, harsh words

    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
     constituer
    0.45
    ش
    0.44
    经常
    0.44
     constitución
    0.43
    authent
    0.43
    绅
    0.43
    經常
    0.42
    并非
    0.41
     Regarding
    0.41
    laboratory
    0.41
    POSITIVE LOGITS
    ぎ
    0.54
    者を
    0.54
     vag
    0.47
     遊
    0.46
    者が
    0.46
    あと
    0.46
    タウン
    0.45
    ers
    0.44
    され
    0.44
    者は
    0.44
    Activations Density 0.000%

    No Known Activations