© 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. 135525
    Prev
    Next
    INDEX
    Explanations

    trends and conditions

    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
    殳
    0.48
    }`)
    0.47
    창
    0.46
    $;
    0.45
    Avec
    0.44
    ่อย
    0.43
    AKE
    0.43
    ښ
    0.43
    യ്ക്ക
    0.42
    enhuma
    0.42
    POSITIVE LOGITS
     Be
    0.50
     Cloud
    0.49
     Wander
    0.48
     Inert
    0.48
     Ste
    0.47
     Vegetation
    0.47
     stem
    0.47
     Zone
    0.47
     vegetation
    0.47
     Regulation
    0.47
    Activations Density 0.001%

    No Known Activations