© 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. 25056
    Prev
    Next
    INDEX
    Explanations

    lists or quantities

    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
    𓐄
    0.49
    cellular
    0.48
    მის
    0.48
    ürm
    0.46
    曠
    0.44
    細胞
    0.41
    лов
    0.40
    識別
    0.40
    StarService
    0.40
    serrat
    0.40
    POSITIVE LOGITS
     SCALE
    0.49
     செய்தால்
    0.45
    式的
    0.45
     Conversely
    0.45
     Haiti
    0.45
    !">
    0.45
     Surprisingly
    0.44
     $$
    0.44
     DRIVE
    0.43
    摒
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.