© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31237
    Prev
    Next
    INDEX
    Explanations

    question mark or period

    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
     zowel
    -1.20
    对于
    -1.10
     extremadamente
    -1.06
    ΰ
    -1.04
    essentially
    -1.00
     wraz
    -0.99
    的气息
    -0.98
    basically
    -0.97
    對於
    -0.96
    igshid
    -0.96
    POSITIVE LOGITS
     yesterday
    1.53
     because
    1.45
    ∅
    1.22
    .');
    1.10
     therefore
    1.07
    /");
    1.06
    .'/
    1.05
     tomorrow
    1.05
     but
    1.05
     tonight
    1.03
    Activations Density 0.038%

    No Known Activations