© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5038
    Prev
    Next
    INDEX
    Explanations

    enabling or spurring growth

    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
     or
    0.17
    ography
    0.17
     
    0.17
    </td>
    0.16
    ের
    0.16
     of
    0.16
     atau
    0.15
    mathrm
    0.15
     أو
    0.15
    5
    0.15
    POSITIVE LOGITS
     us
    0.23
     आपल्याला
    0.19
     untold
    0.19
     आपको
    0.18
     нам
    0.18
     കൂടുതൽ
    0.18
     нас
    0.18
     మరింత
    0.18
    <unused360>
    0.18
     हामी
    0.17
    Activations Density 0.838%

    No Known Activations