© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 487
    Prev
    Next
    INDEX
    Explanations

    email, time, gender, identity

    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_40_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
     psal
    0.49
    blusas
    0.43
     expectancy
    0.43
    ěz
    0.42
     পালন
    0.41
     agglomer
    0.41
    ងឺ
    0.40
    [_
    0.40
    brano
    0.40
    读者
    0.40
    POSITIVE LOGITS
     Poly
    0.41
     Substitute
    0.41
     Locked
    0.40
    Poly
    0.38
     Solve
    0.38
     Th
    0.38
    Locked
    0.38
     Kay
    0.37
    locked
    0.37
     D
    0.37
    Activations Density 0.000%

    No Known Activations