© 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. 108086
    Prev
    Next
    INDEX
    Explanations

    installation and registry items

    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
    ナイ
    -0.73
    ghal
    -0.71
    உ
    -0.70
     ביום
    -0.69
    bites
    -0.69
    ตอบ
    -0.68
    Oral
    -0.68
     Sahib
    -0.67
    electrons
    -0.67
     replacing
    -0.66
    POSITIVE LOGITS
     Center
    0.77
     SMG
    0.66
     Tat
    0.65
     Centre
    0.65
     bangunan
    0.65
     Protobuf
    0.65
     crítico
    0.63
    エク
    0.62
    DialogContent
    0.62
     Κ
    0.62
    Activations Density 0.063%

    No Known Activations