© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146128
    Prev
    Next
    INDEX
    Explanations

    drugs approved

    np_acts-logits-general · gemini-2.5-flash-lite

    optional medical discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ∠
    0.50
    钛
    0.47
    鈦
    0.46
    ☓
    0.43
    疫情
    0.42
    钴
    0.42
    ले
    0.42
    ளு
    0.42
    COVID
    0.41
    屐
    0.41
    POSITIVE LOGITS
    won
    0.42
    ventil
    0.41
     گول
    0.40
    reading
    0.40
    beat
    0.39
    besar
    0.39
    dropping
    0.39
     trail
    0.38
    trail
    0.38
     reading
    0.38
    Activations Density 0.000%

    No Known Activations