© 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. 154532
    Prev
    Next
    INDEX
    Explanations

    straight from

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

    API access for developers

    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
    മാക്കി
    0.51
    SpawnEntry
    0.48
    Squares
    0.48
     મા
    0.47
     народа
    0.46
    Bunch
    0.45
    𒅆
    0.45
    スピ
    0.44
    唝
    0.44
    Depth
    0.44
    POSITIVE LOGITS
    _
    0.45
     wood
    0.45
    лябин
    0.44
    을
    0.43
    f
    0.43
    ING
    0.43
    now
    0.43
     were
    0.42
     lure
    0.41
    4
    0.41
    Activations Density 0.000%

    No Known Activations