© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93009
    Prev
    Next
    INDEX
    Explanations

    topic headings and specific phrases

    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
     ಕೂದಲ
    0.53
     當
    0.52
     នៅ
    0.52
    ững
    0.52
    য়ান
    0.50
     చేస్త
    0.50
     屋
    0.50
     Trên
    0.49
    𒃲
    0.49
    jiwarl
    0.48
    POSITIVE LOGITS
    Per
    0.49
    তা
    0.45
     enough
    0.45
    PD
    0.45
    .
    0.44
     instructions
    0.43
    -
    0.42
    وا
    0.42
    ong
    0.42
     accessibility
    0.42
    Activations Density 0.010%

    No Known Activations