© 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. 174272
    Prev
    Next
    INDEX
    Explanations

    invoice or flyer

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

    #Must_use_phrase_list

    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
    2
    0.58
    stat
    0.46
    name
    0.44
    emails
    0.43
    quot
    0.42
    den
    0.41
    sl
    0.41
    rike
    0.41
    scheme
    0.40
    begin
    0.40
    POSITIVE LOGITS
     అనుమ
    0.52
    滉
    0.50
     फाइनल
    0.50
     municipios
    0.49
     پژوه
    0.49
     벡터
    0.47
     ventricle
    0.47
     comodidad
    0.47
     fluidity
    0.46
     tenga
    0.46
    Activations Density 0.000%

    No Known Activations