© 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. 40-GEMMASCOPE-2-RES-262K
    7. 193315
    Prev
    Next
    INDEX
    Explanations

    checks if opened

    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
     Gaston
    0.45
     rung
    0.43
     Journalism
    0.40
     Eugene
    0.40
     splinter
    0.40
    㥽
    0.38
    Eugene
    0.37
     PE
    0.37
     Engines
    0.37
     cassette
    0.36
    POSITIVE LOGITS
     анато
    0.41
    漢字
    0.39
    ExpressCheckout
    0.38
    Ũ
    0.38
     amicable
    0.38
    ኹ
    0.37
    Explain
    0.37
    risy
    0.37
    spě
    0.37
    bsch
    0.37
    Activations Density 0.003%

    No Known Activations