© 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. 159320
    Prev
    Next
    INDEX
    Explanations

    person wanting elements and ice

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

    foreign languages and specific terms

    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
    is
    0.53
    Vox
    0.47
    Via
    0.46
    finally
    0.46
     premieres
    0.45
    Homes
    0.44
     ত
    0.44
    celebr
    0.44
    Walls
    0.44
    Grid
    0.43
    POSITIVE LOGITS
     जूस
    0.56
     θερ
    0.52
     dışında
    0.51
     손
    0.49
     dosa
    0.49
    鳜
    0.49
     ఆమె
    0.49
     그녀
    0.49
    錒
    0.49
     conoz
    0.48
    Activations Density 0.000%

    No Known Activations