© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 295
    Prev
    Next
    INDEX
    Explanations

    keras, kernel, kerberos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    વાર
    0.47
     floribus
    0.44
    ا
    0.43
    有り
    0.43
     caldo
    0.42
     IUnary
    0.40
    厶
    0.39
     इंपॉर्टेंट
    0.39
    BESCHREIBUNG
    0.39
     katva
    0.38
    POSITIVE LOGITS
     Ker
    0.62
    Ker
    0.62
     케
    0.59
     ker
    0.56
     ケ
    0.55
    beros
    0.52
     Ке
    0.51
     KER
    0.51
    K
    0.48
     K
    0.45
    Activations Density 0.013%

    No Known Activations