© 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. 48247
    Prev
    Next
    INDEX
    Explanations

    words + punctuation

    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
    то
    0.54
    бро
    0.51
    ন
    0.50
    น
    0.50
    к
    0.49
    प
    0.49
    ंचल
    0.48
     собі
    0.47
    у
    0.47
    кл
    0.46
    POSITIVE LOGITS
     European
    0.54
     جا
    0.53
    usaha
    0.51
     Carter
    0.46
     Shakespeare
    0.45
     Washington
    0.45
     Lian
    0.45
     Gaz
    0.45
     Cupid
    0.45
     Trump
    0.43
    Activations Density 0.008%

    No Known Activations