© 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. 32203
    Prev
    Next
    INDEX
    Explanations

    Cli, Clipper, Climatology, Clippy

    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
    ってください
    -0.82
    titles
    -0.82
     virtu
    -0.82
    dorfer
    -0.70
     coven
    -0.70
     terme
    -0.70
    oaks
    -0.69
    Ố
    -0.68
    vač
    -0.68
    nake
    -0.68
    POSITIVE LOGITS
     Cli
    1.46
     cli
    1.45
    Cli
    1.38
    cli
    1.24
     Кли
    1.20
     клі
    1.13
     кли
    1.11
    Кли
    1.10
     CLI
    1.00
     clippings
    0.95
    Activations Density 0.018%

    No Known Activations