© 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. 78135
    Prev
    Next
    INDEX
    Explanations

    telecom and telephone industry

    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
     wollt
    -0.95
     thermostat
    -0.90
    Telefono
    -0.89
    Tatiana
    -0.85
     throttle
    -0.83
     même
    -0.83
    Teatro
    -0.83
    Assignments
    -0.82
    Natalia
    -0.82
    Anak
    -0.82
    POSITIVE LOGITS
    muting
    1.09
    pate
    0.96
    interpreted
    0.90
     Bidding
    0.87
    apse
    0.87
    drinking
    0.87
    aniline
    0.87
    nical
    0.86
     łatwo
    0.86
    inage
    0.85
    Activations Density 0.016%

    No Known Activations