© 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. 184277
    Prev
    Next
    INDEX
    Explanations

    in the house

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

    discussing strategies and suggestions

    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
    -
    0.50
     Wiley
    0.46
     w
    0.43
    asil
    0.43
     wis
    0.42
    swire
    0.41
    ii
    0.41
    ัง
    0.40
     shake
    0.40
     y
    0.40
    POSITIVE LOGITS
    鶘
    0.48
     озера
    0.45
     breaching
    0.45
    λού
    0.45
    Лю
    0.45
     गांवों
    0.45
    Он
    0.45
     Tuscany
    0.44
     региона
    0.44
    Під
    0.44
    Activations Density 0.000%

    No Known Activations