© 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. 189293
    Prev
    Next
    INDEX
    Explanations

    counting numerical values

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

    requires specific or permission

    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
     रीठा
    0.46
     വില
    0.45
     КО
    0.44
     கெல்
    0.44
    лән
    0.43
     ね
    0.43
    缇
    0.43
    зи
    0.42
     ফুল
    0.42
     देवगन
    0.42
    POSITIVE LOGITS
    ous
    0.51
    mau
    0.51
    uma
    0.50
     adrenergic
    0.49
    mur
    0.48
    érant
    0.48
    akin
    0.47
     dni
    0.47
    ants
    0.47
     physician
    0.47
    Activations Density 0.000%

    No Known Activations