© 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. 244734
    Prev
    Next
    INDEX
    Explanations

    . and limit of

    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
    DISPLAY
    0.52
    版
    0.49
    Decoder
    0.46
    lectricité
    0.45
    版的
    0.44
    شك
    0.44
     mehr
    0.43
    LEXPORT
    0.43
    +","
    0.43
     Geheim
    0.43
    POSITIVE LOGITS
     ranged
    0.46
     Crohn
    0.46
    ẵn
    0.45
     PubMed
    0.44
     Career
    0.43
    ews
    0.43
    zi
    0.42
     PTSD
    0.42
     bial
    0.42
     trypsin
    0.41
    Activations Density 0.000%

    No Known Activations