© 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. 49883
    Prev
    Next
    INDEX
    Explanations

    anything new

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

    synonym or alternative phrasing

    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
    م
    0.80
    м
    0.57
    m
    0.56
    mature
    0.54
    on
    0.53
    historical
    0.52
    month
    0.51
    Month
    0.50
    ం
    0.50
    as
    0.49
    POSITIVE LOGITS
     voitures
    0.55
     цвет
    0.54
     আছি
    0.50
     कारों
    0.50
     χρώ
    0.50
     গাড়ি
    0.50
     способны
    0.49
    配色
    0.48
     場合
    0.48
     مسلح
    0.48
    Activations Density 0.000%

    No Known Activations