© 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. 69869
    Prev
    Next
    INDEX
    Explanations

    definitions and details

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

    conditions or requirements

    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
    ज
    0.59
    SE
    0.55
    CONNECTION
    0.54
    ALL
    0.53
     are
    0.52
    㥳
    0.52
    हन
    0.50
    MAN
    0.49
    FALL
    0.49
    お願い致します
    0.49
    POSITIVE LOGITS
    etten
    0.48
    :“
    0.46
     দফ
    0.46
    っていました
    0.46
     Vicente
    0.45
     chaired
    0.45
    ñones
    0.45
    rinde
    0.44
    क्रोस
    0.43
    PerTrial
    0.43
    Activations Density 0.000%

    No Known Activations