© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33113
    Prev
    Next
    INDEX
    Explanations

    migrations, magician

    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
    愛的
    0.45
    铷
    0.44
     ओन
    0.42
    எல்
    0.42
    Ṭ
    0.41
     انھوں
    0.41
     दुल्हन
    0.40
     Effekt
    0.40
    亣
    0.40
    setDisplay
    0.39
    POSITIVE LOGITS
     document
    0.45
     descent
    0.43
     potentially
    0.39
     derivatives
    0.38
    classify
    0.38
    document
    0.38
     modification
    0.38
     brave
    0.38
     predict
    0.38
     deviate
    0.38
    Activations Density 0.000%

    No Known Activations