© 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. 110468
    Prev
    Next
    INDEX
    Explanations

    actions and tasks

    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
    <em>
    0.37
    的市场
    0.37
    ?!"
    0.34
    ς
    0.34
    sstream
    0.33
    󠁢
    0.32
    sales
    0.32
    <0xA0>
    0.32
     स्ट्रा
    0.32
    ském
    0.32
    POSITIVE LOGITS
     iki
    0.41
     irregularities
    0.40
     zwei
    0.39
     macrophages
    0.38
     disadvantages
    0.38
     léger
    0.37
     hierro
    0.37
     legger
    0.36
     WITH
    0.36
     dengan
    0.35
    Activations Density 0.067%

    No Known Activations