© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130513
    Prev
    Next
    INDEX
    Explanations

    calculator for tests

    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
    شته
    0.40
    パート
    0.38
     क्वेश्चंस
    0.37
     elementary
    0.37
    小題
    0.36
     अगेन
    0.36
    ᄏ
    0.36
    體驗
    0.35
     Elementary
    0.35
    ֻ
    0.35
    POSITIVE LOGITS
     Colin
    0.46
    Coleman
    0.44
     Coleman
    0.43
     speaks
    0.42
     coles
    0.42
     ciem
    0.40
    计算
    0.38
     Speak
    0.38
    Wikimedia
    0.38
     calculadora
    0.38
    Activations Density 0.005%

    No Known Activations