© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14377
    Prev
    Next
    INDEX
    Explanations

    html code

    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_40_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
    📌
    0.40
     dist
    0.39
     termination
    0.39
     plak
    0.39
    終了
    0.38
     önceki
    0.38
     English
    0.38
    롤
    0.38
     clippings
    0.38
     kren
    0.38
    POSITIVE LOGITS
    Nb
    0.42
    Ni
    0.41
    libraries
    0.41
    Coefficient
    0.41
    KBr
    0.39
    Yo
    0.39
    暮
    0.39
    Mb
    0.39
    Stefan
    0.39
    骂
    0.38
    Activations Density 0.001%

    No Known Activations