© 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. 773
    Prev
    Next
    INDEX
    Explanations

    software version suffixes

    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
    Cancellation
    0.40
     очереди
    0.39
    Aaron
    0.38
    AMOUNT
    0.37
    ^{*}
    0.37
    الصف
    0.36
    HTTP
    0.36
    ୮
    0.36
    شش
    0.35
    intensité
    0.35
    POSITIVE LOGITS
     Beta
    0.55
     beta
    0.53
    Beta
    0.48
    beta
    0.47
    SNAPSHOT
    0.46
     patch
    0.45
    RELEASE
    0.44
     roll
    0.43
     nightly
    0.43
     capricious
    0.43
    Activations Density 0.006%

    No Known Activations