© 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. 23831
    Prev
    Next
    INDEX
    Explanations

    excellent or strong skills

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

    excellent or strong communication and problem-solving

    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
     சேர்ந்த
    0.56
     Jimenez
    0.46
     invigorating
    0.45
     अनुसार
    0.44
    ට
    0.44
     realizan
    0.44
     dilig
    0.43
     जूनियर
    0.43
     algún
    0.42
    sdf
    0.41
    POSITIVE LOGITS
    聯繫
    0.47
    مق
    0.46
    文字
    0.40
    rende
    0.40
    renn
    0.40
     كلمه
    0.40
    اقه
    0.39
    pO
    0.39
    াস্থ্যের
    0.38
    譎
    0.38
    Activations Density 0.002%

    No Known Activations