© 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. 50330
    Prev
    Next
    INDEX
    Explanations

    drug discovery

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

    seeing already

    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
    折
    0.47
    ardo
    0.46
    合
    0.45
     బీ
    0.42
    <0x0D>
    0.42
    ↵
    0.42
     克
    0.41
    ili
    0.41
    obra
    0.41
    opy
    0.40
    POSITIVE LOGITS
    Groups
    0.50
    몇
    0.47
     tenderness
    0.47
    ある
    0.46
    MyShop
    0.46
     poise
    0.46
    gives
    0.44
     rares
    0.44
     রোগের
    0.44
    quefois
    0.43
    Activations Density 0.000%

    No Known Activations