© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 234135
    Prev
    Next
    INDEX
    Explanations

    agent, supervisor, owner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Varsity
    0.47
    nominated
    0.47
     ಕೊಟ್ಟ
    0.46
    substring
    0.45
    fang
    0.44
    +"|
    0.43
     दौड़
    0.43
    ज़न
    0.43
    }$')
    0.43
    izontally
    0.43
    POSITIVE LOGITS
    就不
    0.49
     inférieure
    0.48
     calles
    0.46
    ار
    0.46
    묽
    0.45
     envers
    0.44
     chamado
    0.44
     commencent
    0.44
     bearer
    0.44
     sper
    0.43
    Activations Density 0.001%

    No Known Activations