© 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. 10-GEMMASCOPE-RES-131K
    7. 13839
    Prev
    Next
    INDEX
    Explanations

    quoted phrases and their beginnings

    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
     semelh
    -2.16
    
    -2.14
    𓁹
    -2.11
    亹
    -2.11
    蛱
    -2.09
     grotte
    -2.08
    ఽ
    -2.05
    
    -2.05
    ￬
    -2.00
    ୬
    -1.99
    POSITIVE LOGITS
     There
    2.63
     any
    2.31
     Since
    2.19
     in
    2.14
     Why
    2.08
     and
    2.08
     Despite
    2.05
     Following
    2.03
     an
    2.02
     Probably
    1.99
    Activations Density 0.058%

    No Known Activations