© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31375
    Prev
    Next
    INDEX
    Explanations

    Environment.getExternalStorageDirectory()

    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
     barrera
    -0.70
     бассей
    -0.67
    バッ
    -0.65
    astic
    -0.65
     обуви
    -0.63
    该公司
    -0.62
    Hoe
    -0.62
    コラ
    -0.61
    EEE
    -0.61
    Tiles
    -0.61
    POSITIVE LOGITS
    στό
    0.74
     davidson
    0.74
     lom
    0.69
    fmt
    0.69
    าม
    0.68
    зовый
    0.65
    ANTIC
    0.64
     地方
    0.63
     emptiness
    0.63
     Pigeon
    0.63
    Activations Density 0.062%

    No Known Activations