© 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. 131309
    Prev
    Next
    INDEX
    Explanations

    understanding deeper

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

    statement requests

    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
     декабря
    0.47
     первого
    0.47
     vem
    0.45
    炅
    0.44
     bened
    0.44
    лы
    0.44
    ץ
    0.44
     Zas
    0.44
    ه
    0.44
     Engel
    0.43
    POSITIVE LOGITS
     elastomers
    0.49
     मजब
    0.48
     اہم
    0.47
     expenditures
    0.47
     injunctive
    0.47
     esigen
    0.47
    getPackageName
    0.45
    APPED
    0.45
     inserir
    0.45
    skirts
    0.44
    Activations Density 0.001%

    No Known Activations