© 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. 807
    Prev
    Next
    INDEX
    Explanations

    bootstrap css links

    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
    qttr
    0.45
    UISelectors
    0.42
     decal
    0.41
    ElementSibling
    0.41
    尿
    0.40
     پرا
    0.40
    Moscow
    0.39
    Peru
    0.39
     Mosk
    0.38
    喰
    0.38
    POSITIVE LOGITS
     Bootstrap
    1.44
     bootstrap
    1.31
    Bootstrap
    1.26
    bootstrap
    1.23
     bootstra
    0.94
     Boots
    0.89
     bootstrapping
    0.88
    BOOT
    0.86
    glyphicon
    0.85
     boots
    0.84
    Activations Density 0.005%

    No Known Activations