© 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. 144380
    Prev
    Next
    INDEX
    Explanations

    lists and programming comments

    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
     اقصیٰ
    0.52
    ㇁
    0.52
    anager
    0.45
    aird
    0.45
    프트
    0.44
     gerçekleştir
    0.44
    修士
    0.43
    رسٹ
    0.43
    ！】
    0.43
    새
    0.42
    POSITIVE LOGITS
     public
    0.48
     so
    0.48
     float
    0.46
    fZ
    0.46
     f
    0.44
     =
    0.44
     turmoil
    0.44
     restore
    0.44
    public
    0.43
     debate
    0.43
    Activations Density 0.000%

    No Known Activations