© 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. 34-GEMMASCOPE-RES-131K
    7. 92991
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters

    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
    ၇
    -0.88
     really
    -0.87
     seemed
    -0.86
    لاث
    -0.86
     meticulously
    -0.85
     alturas
    -0.85
    What
    -0.85
     suggests
    -0.84
     localidades
    -0.84
     initiatives
    -0.83
    POSITIVE LOGITS
    갸
    0.94
    personal
    0.90
    extremely
    0.89
    ESSMENT
    0.87
    stract
    0.87
    ENDA
    0.87
    following
    0.85
     overly
    0.84
    などが
    0.83
     woll
    0.83
    Activations Density 0.013%

    No Known Activations