© 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. 51084
    Prev
    Next
    INDEX
    Explanations

    key performance, system, JSON, directly

    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
    על
    0.52
     เด็ก
    0.49
    "@
    0.47
    ]@
    0.47
     Squirrel
    0.46
     Mà
    0.45
     جائزے
    0.44
    山区
    0.44
    𝑻
    0.44
     ጠ
    0.43
    POSITIVE LOGITS
     mets
    0.49
    2
    0.48
     tekst
    0.47
     Gewicht
    0.47
    arsk
    0.46
     secs
    0.45
    novo
    0.45
     Australie
    0.44
    downloads
    0.44
     prior
    0.42
    Activations Density 0.001%

    No Known Activations