© 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. 169174
    Prev
    Next
    INDEX
    Explanations

    within modern

    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
    ⿰
    0.42
     udal
    0.38
    randomNumber
    0.37
    akana
    0.37
    ąda
    0.36
    UILLER
    0.36
    墺
    0.36
     elytris
    0.36
     المخت
    0.36
    <unused33>
    0.36
    POSITIVE LOGITS
     Ice
    0.49
     Tenant
    0.48
     ice
    0.46
     Tenants
    0.45
     Rockets
    0.44
     Amanda
    0.44
     IC
    0.44
     Season
    0.44
     RNA
    0.43
     Babies
    0.43
    Activations Density 0.000%

    No Known Activations