© 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. 200107
    Prev
    Next
    INDEX
    Explanations

    check all

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

    identification numbers and names

    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
    ㄆ
    0.51
     hidrográf
    0.49
    dbjc
    0.46
    鋸
    0.46
    FBSDKError
    0.45
     китай
    0.44
    obao
    0.43
    獲得
    0.43
    umpang
    0.43
    china
    0.42
    POSITIVE LOGITS
     utterances
    0.56
    ?
    0.52
    Check
    0.51
    ).}
    0.49
     ASX
    0.47
    Exercise
    0.47
    ն
    0.46
    ?).
    0.46
     Богу
    0.45
    Centre
    0.45
    Activations Density 0.000%

    No Known Activations