© 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. 233285
    Prev
    Next
    INDEX
    Explanations

    plan sample, leave live

    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
     يف
    0.54
    ре
    0.52
    り
    0.52
    designer
    0.51
     пайда
    0.51
    tiered
    0.51
    novo
    0.51
    candy
    0.51
    mushroom
    0.50
     propriété
    0.49
    POSITIVE LOGITS
     abre
    0.45
    Ν
    0.45
    SIX
    0.44
     vun
    0.44
     createUser
    0.43
     Mannschaft
    0.43
    Ο
    0.43
     विरु
    0.42
     SE
    0.42
     Nd
    0.41
    Activations Density 0.000%

    No Known Activations