© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19078
    Prev
    Next
    INDEX
    Explanations

    intercept, forwards, type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    3
    0.63
    4
    0.62
     be
    0.61
     in
    0.61
    6
    0.59
    2
    0.57
     T
    0.51
     tr
    0.50
    5
    0.50
     pl
    0.49
    POSITIVE LOGITS
    妧
    0.54
    ląd
    0.52
    Loksatta
    0.51
    FindingsResponse
    0.51
    ব্ধ
    0.49
    RetResult
    0.49
    Daten
    0.48
     informée
    0.48
    Bild
    0.48
    🍵
    0.48
    Activations Density 0.003%

    No Known Activations