© 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. 66401
    Prev
    Next
    INDEX
    Explanations

    visual texture and surface properties

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

    salt crystallization or sugar solution

    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
    豺
    0.57
     अन्याय
    0.55
    𝔯
    0.54
     घोषणा
    0.53
     पुरस्कार
    0.53
     ऐतिहासिक
    0.53
    akespeare
    0.52
    弑
    0.52
    颁
    0.52
     политики
    0.51
    POSITIVE LOGITS
     pixels
    0.81
     calc
    0.76
     color
    0.75
     surface
    0.71
     granules
    0.71
     texture
    0.70
     filaments
    0.70
     cortical
    0.69
     substrate
    0.68
     grains
    0.68
    Activations Density 0.000%

    No Known Activations