© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100700
    Prev
    Next
    INDEX
    Explanations

    compute identify learning

    np_acts-logits-general · gemini-2.5-flash-lite

    verbs related to performing, executing, or carrying out actions or processes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     PRODUCTO
    -1.15
    }):
    -1.13
    Maß
    -1.11
    Verwendung
    -1.09
     теперь
    -1.07
    ору
    -1.07
     ewig
    -1.05
     décé
    -1.05
     behö
    -1.03
     menyebut
    -1.02
    POSITIVE LOGITS
     and
    1.08
     who
    1.05
     -
    1.04
     Intrinsic
    0.98
     bds
    0.96
    newPassword
    0.93
     altres
    0.92
    不觉
    0.91
    iestety
    0.89
     himself
    0.88
    Activations Density 0.930%

    No Known Activations