© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23759
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     =
    0.39
    骰
    0.39
    人和
    0.35
    e
    0.35
    已知
    0.34
    lum
    0.34
    f
    0.33
     reconstructed
    0.33
    r
    0.33
     ጡ
    0.33
    POSITIVE LOGITS
     balconies
    0.44
    feitura
    0.37
     plazas
    0.36
    ósticos
    0.36
     plantations
    0.36
     chandeliers
    0.36
     exorbitant
    0.35
     allotments
    0.35
     балко
    0.35
    フォル
    0.35
    Activations Density 0.060%

    No Known Activations