© 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. 191329
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation or specific words

    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
    滋
    0.47
    icoes
    0.40
    㣱
    0.40
    癖
    0.40
    鋒
    0.38
    栃木
    0.38
     Sección
    0.38
     deserialize
    0.37
    纖
    0.37
    MM
    0.36
    POSITIVE LOGITS
    ujo
    0.37
     अरुण
    0.36
     বন্দ্য
    0.36
     acquaintance
    0.35
     acquainted
    0.34
     caravans
    0.34
     accent
    0.34
     Tulum
    0.34
     captive
    0.33
     grond
    0.33
    Activations Density 0.011%

    No Known Activations