© 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. 112512
    Prev
    Next
    INDEX
    Explanations

    financial, legal, and abstract terms

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

    consolidated group, column, taught, generates, assisting

    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
    descriptor
    0.51
     éto
    0.50
    Just
    0.49
    vore
    0.45
    et
    0.44
     equilibrio
    0.44
    AA
    0.44
    _
    0.43
     verdadeiro
    0.43
    DESCRIPTOR
    0.42
    POSITIVE LOGITS
     판매
    0.49
    вим
    0.47
    शुल्क
    0.46
    NetAmount
    0.46
     зимо
    0.46
    ത്തിനും
    0.46
     Mö
    0.45
    rawData
    0.45
    娉
    0.45
     keber
    0.45
    Activations Density 0.000%

    No Known Activations