© 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. 48084
    Prev
    Next
    INDEX
    Explanations

    surgeon operating

    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
    みの
    0.45
    <unused26>
    0.43
    栄養
    0.43
     пя
    0.43
    ša
    0.42
     সর্বশেষ
    0.42
    きの
    0.40
    欴
    0.40
     मेरा
    0.40
     기억
    0.40
    POSITIVE LOGITS
     softer
    0.43
     incipient
    0.41
     softened
    0.40
     rethink
    0.40
     lighter
    0.39
     ajout
    0.39
     soften
    0.39
     autrefois
    0.39
     softens
    0.38
     calmer
    0.38
    Activations Density 0.011%

    No Known Activations