© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108089
    Prev
    Next
    INDEX
    Explanations

    loan Limited

    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
    [{\
    0.47
     briefed
    0.44
     gyakor
    0.43
     Sadh
    0.43
     Machine
    0.43
     Warranty
    0.42
     Dred
    0.42
     Bird
    0.42
    ën
    0.42
     studied
    0.41
    POSITIVE LOGITS
    𝚟
    0.53
    و
    0.51
    𝚓
    0.51
    NERVE
    0.48
    전히
    0.48
    ต
    0.47
    ことも
    0.47
    미
    0.46
    𝙵
    0.46
    나
    0.46
    Activations Density 0.002%

    No Known Activations