© 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. 17463
    Prev
    Next
    INDEX
    Explanations

    news and updates

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

    list separators and conjunctions

    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
    տ
    0.50
    θέ
    0.44
    პი
    0.44
     '%'
    0.43
    роид
    0.43
    ⌵
    0.42
    کل
    0.42
    ដែលអាច
    0.41
    тою
    0.40
    ວກ
    0.40
    POSITIVE LOGITS
     sawdust
    0.42
     counselling
    0.41
     Busch
    0.40
     v
    0.39
     P
    0.39
     Green
    0.39
     Little
    0.39
     Answers
    0.39
    0.39
     Cottage
    0.38
    Activations Density 0.000%

    No Known Activations