© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    here's how a

    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
    させる
    0.40
    する
    0.39
    하는
    0.39
    하여
    0.38
     ומ
    0.37
    ད
    0.37
     하여
    0.37
    使
    0.35
     如何
    0.34
     alimentation
    0.34
    POSITIVE LOGITS
    one
    0.47
     была
    0.46
     були
    0.46
     были
    0.44
     было
    0.44
     została
    0.43
    aliśmy
    0.43
     был
    0.43
     weren
    0.42
     ήταν
    0.41
    Activations Density 0.004%

    No Known Activations