© 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. 146280
    Prev
    Next
    INDEX
    Explanations

    categories and specific types

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

    case statement

    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
     লিখিত
    0.51
     Ό
    0.49
     ఆర్థిక
    0.48
     संरक्षक
    0.48
     সৈয়দ
    0.47
    参数向量
    0.46
     ట
    0.45
    జి
    0.45
     القر
    0.44
     অনুষ্ঠানে
    0.44
    POSITIVE LOGITS
    Thermal
    0.52
    THE
    0.48
    the
    0.47
    Sunrise
    0.46
    National
    0.46
    Japanese
    0.46
    thed
    0.45
    Global
    0.45
    Stainless
    0.44
    नई
    0.44
    Activations Density 0.001%

    No Known Activations