© 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. 31-GEMMASCOPE-2-RES-262K
    7. 204096
    Prev
    Next
    INDEX
    Explanations

    return to original life

    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_31_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
    ट
    0.51
    ע
    0.49
     veľ
    0.49
     zajed
    0.47
    रुख
    0.47
     metabolite
    0.47
     Sophomore
    0.47
    ιβ
    0.46
     CryptoJS
    0.46
     vozila
    0.46
    POSITIVE LOGITS
    <unused57>
    0.48
    mented
    0.48
    课
    0.47
    Getty
    0.45
    spanning
    0.45
    gore
    0.44
     परंपरागत
    0.44
    Say
    0.44
     регулярно
    0.44
    pubs
    0.43
    Activations Density 0.000%

    No Known Activations