© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32021
    Prev
    Next
    INDEX
    Explanations

    movement and exploration

    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_all/layer_41_width_262k_l0_big
    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
     대비
    0.41
     கொண்டனர்
    0.39
     curved
    0.38
    ವಿ
    0.38
     orada
    0.38
     discutir
    0.38
    考慮
    0.37
    蚩
    0.37
    ㄙ
    0.37
     গভীরভাবে
    0.36
    POSITIVE LOGITS
     hopping
    1.17
    hopping
    0.97
     hop
    0.85
     hopped
    0.82
     roving
    0.82
    Hop
    0.82
     touring
    0.80
     hops
    0.79
     circuit
    0.76
     roaming
    0.76
    Activations Density 0.002%

    No Known Activations