© 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. 62241
    Prev
    Next
    INDEX
    Explanations

    the historic

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

    awareness of acceptance

    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
    这时
    0.45
    Phone
    0.45
    strstr
    0.44
    壁
    0.44
    ଏ
    0.44
    వలం
    0.43
     চা
    0.43
    比如
    0.42
    切割
    0.42
    鐳
    0.41
    POSITIVE LOGITS
     months
    0.50
     contribution
    0.48
     nomes
    0.48
     volunteered
    0.48
     contributed
    0.47
     ousted
    0.47
     volunte
    0.46
     Ange
    0.46
     Declan
    0.46
     annexed
    0.46
    Activations Density 0.000%

    No Known Activations