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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 170051
    Prev
    Next
    INDEX
    Explanations

    linking word followed by concept

    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
     tensors
    0.40
     ===============
    0.39
    きたいと思います
    0.39
     Removing
    0.38
    <0x96>
    0.38
    রাও
    0.38
     роди
    0.36
     рас
    0.35
    改变
    0.35
    ีน
    0.35
    POSITIVE LOGITS
    燔
    0.55
    चा
    0.53
    匏
    0.50
     achats
    0.49
    s
    0.49
    ワールド
    0.49
    o
    0.49
     unripe
    0.48
    喈
    0.48
    䝬
    0.48
    Activations Density 0.000%

    No Known Activations