© 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. 201113
    Prev
    Next
    INDEX
    Explanations

    gentle, curious, herd animals

    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
    䔋
    0.56
     ინტერ
    0.51
    looked
    0.50
    automatic
    0.49
    landish
    0.48
     interdependence
    0.47
     invertible
    0.47
    therefore
    0.46
    INED
    0.46
    TAIN
    0.45
    POSITIVE LOGITS
    0.49
    صف
    0.48
    ිරි
    0.44
    沟
    0.43
    ည့်
    0.42
    '
    0.42
    <
    0.40
    ضيع
    0.40
     doba
    0.39
     adecuadas
    0.39
    Activations Density 0.004%

    No Known Activations