© 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. 245903
    Prev
    Next
    INDEX
    Explanations

    financial shares and numbers

    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
     ジュ
    0.51
     女の子
    0.49
     downgraded
    0.48
     レディース
    0.48
     పొంద
    0.47
    ፣
    0.47
     ට
    0.46
     flee
    0.46
     教え
    0.46
     軽量
    0.45
    POSITIVE LOGITS
    س
    0.53
    ס
    0.52
    -
    0.49
    Über
    0.49
    REVIEW
    0.46
    WITH
    0.46
    한편
    0.46
    사회
    0.45
    с
    0.45
    fü
    0.45
    Activations Density 0.001%

    No Known Activations