© 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. 91830
    Prev
    Next
    INDEX
    Explanations

    options and context

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

    abstract, class, database

    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
    maine
    0.53
    INE
    0.50
    requested
    0.48
    人士
    0.46
    ASES
    0.46
     eingestellt
    0.46
    inue
    0.45
     ਤ
    0.45
     boon
    0.45
     ausdr
    0.45
    POSITIVE LOGITS
    鍝
    0.41
     Patrimonio
    0.41
    高端
    0.41
    bindingNavigator
    0.40
    ைகளும்
    0.40
    ضای
    0.40
     raving
    0.39
    부를
    0.39
     barang
    0.39
     Harbour
    0.39
    Activations Density 0.000%

    No Known Activations