© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 218973
    Prev
    Next
    INDEX
    Explanations

    made directly

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

    Flutter widget key parameter

    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
     devrez
    0.50
    ए
    0.47
     devra
    0.47
    नेट
    0.47
    प
    0.47
    पाउंड
    0.46
    Liverpool
    0.46
     कपकेक
    0.46
    রবি
    0.45
    ∘
    0.45
    POSITIVE LOGITS
     Mic
    0.46
    ائية
    0.46
    dessä
    0.43
     últimas
    0.42
    Gilbert
    0.41
    ائي
    0.40
    iram
    0.40
     cik
    0.40
     cic
    0.39
    ttä
    0.39
    Activations Density 0.000%

    No Known Activations