© 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. 31458
    Prev
    Next
    INDEX
    Explanations

    people, roles, and activities

    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
     perek
    -1.21
     italia
    -1.14
    vaila
    -1.10
    嬸
    -1.04
     itali
    -1.02
     中國
    -1.02
     cabine
    -1.01
     tait
    -1.00
    isling
    -1.00
    ---->
    -1.00
    POSITIVE LOGITS
     multiplier
    1.07
     actors
    1.06
     NEET
    1.05
    NEET
    1.05
     compet
    1.05
     EU
    1.05
    zanas
    1.01
    cault
    1.00
     повіт
    0.99
     trainers
    0.99
    Activations Density 0.026%

    No Known Activations