© 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. 150931
    Prev
    Next
    INDEX
    Explanations

    local government and service

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

    items after bullet points

    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
    ن
    0.61
    د
    0.55
    न
    0.51
    dą
    0.48
    p
    0.48
    ب
    0.48
    ರಿದ
    0.47
    తం
    0.47
    ologías
    0.47
    锐
    0.46
    POSITIVE LOGITS
    issez
    0.48
     gouvernement
    0.48
     আইনশৃঙ্খলা
    0.47
     Boulevard
    0.46
     laufen
    0.46
    reibung
    0.44
     للط
    0.43
     beantwort
    0.42
     dienst
    0.42
     Polizei
    0.41
    Activations Density 0.000%

    No Known Activations