© 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. 10-GEMMASCOPE-RES-131K
    7. 73353
    Prev
    Next
    INDEX
    Explanations

    credential and Cumberland

    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_10/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
    癀
    -2.63
    逦
    -2.58
    ズニー
    -2.55
    鹚
    -2.52
     icône
    -2.45
    窳
    -2.44
    𖣘
    -2.39
    棐
    -2.38
    AddWithValue
    -2.36
    錞
    -2.36
    POSITIVE LOGITS
    ized
    2.92
    ata
    2.92
    ed
    2.75
    “
    2.59
    er
    2.55
    ing
    2.50
    ated
    2.50
    但她
    2.50
    2
    2.47
    ～～
    2.41
    Activations Density 0.003%

    No Known Activations