© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204468
    Prev
    Next
    INDEX
    Explanations

    salvation, current, stations, now

    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
    ClearedBy
    0.59
     ተግባ
    0.55
     (-)
    0.52
     těž
    0.51
     იგი
    0.51
     concealment
    0.50
     chiefly
    0.50
     መድሃኒ
    0.49
     rackets
    0.48
     zvý
    0.48
    POSITIVE LOGITS
    Q
    0.59
    5
    0.57
    9
    0.57
    8
    0.54
    2
    0.50
    {
    0.49
    А
    0.47
    7
    0.47
    ОО
    0.47
    З
    0.46
    Activations Density 0.001%

    No Known Activations