© 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. 74592
    Prev
    Next
    INDEX
    Explanations

    specific option or event

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

    stage, fundamental, focused

    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
    ॔
    0.54
    ឍ
    0.53
     व्यवसाय
    0.50
     Ophthalm
    0.50
     arXiv
    0.49
    politics
    0.49
    ษัท
    0.48
     biznes
    0.48
    antaranya
    0.47
     ล
    0.47
    POSITIVE LOGITS
    YO
    0.44
    abon
    0.42
    ändert
    0.41
    ähler
    0.41
     haver
    0.40
     aide
    0.39
    UTE
    0.39
    TableRow
    0.38
     einf
    0.38
     assistants
    0.38
    Activations Density 0.000%

    No Known Activations