© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116238
    Prev
    Next
    INDEX
    Explanations

    Denied or granted court decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erover
    -0.75
     分析
    -0.72
     پرداخت
    -0.71
    ]}>
    -0.70
    Kee
    -0.69
    ัฒนา
    -0.69
    Credential
    -0.68
     |=
    -0.68
    CheckBreak
    -0.67
     Beg
    -0.66
    POSITIVE LOGITS
    ethanol
    0.76
    koi
    0.72
    DEPREC
    0.69
     ethanol
    0.68
    Assemble
    0.68
    LPD
    0.68
    LPT
    0.68
    Horiz
    0.68
    brews
    0.67
    alang
    0.66
    Activations Density 0.049%

    No Known Activations