© 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. 151980
    Prev
    Next
    INDEX
    Explanations

    income, state, booked, artist

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

    guidelines and timeouts

    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
    ônico
    0.47
    ด
    0.44
    규
    0.43
    那时候
    0.42
    刹
    0.42
    ärte
    0.42
     शहनाज
    0.42
    和一个
    0.41
     archivo
    0.40
    ข
    0.40
    POSITIVE LOGITS
    欣赏
    0.57
    欣賞
    0.56
    ভেদ
    0.52
    income
    0.50
    ci
    0.48
    iterate
    0.48
    itime
    0.47
    booked
    0.46
    state
    0.45
    BO
    0.45
    Activations Density 0.000%

    No Known Activations