© 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. 64882
    Prev
    Next
    INDEX
    Explanations

    National University, predictive marker, http

    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
    ври
    -0.69
     disgusted
    -0.67
    microbial
    -0.66
    ITUDE
    -0.65
    vanje
    -0.65
    laz
    -0.65
     dismay
    -0.65
    ông
    -0.65
    inity
    -0.64
     appears
    -0.64
    POSITIVE LOGITS
    मिक
    0.68
    ἃ
    0.67
     database
    0.67
    舔
    0.66
    likely
    0.65
    SALUD
    0.65
     ornate
    0.65
    QUÉ
    0.65
    Autriche
    0.65
    共演
    0.65
    Activations Density 0.060%

    No Known Activations