© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    Gemma team safety guidelines

    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
     demonstrations
    0.46
    :
    0.46
     complements
    0.44
     inputs
    0.40
     input
    0.40
     humanitarian
    0.40
     হচ্ছে
    0.39
     translate
    0.39
     complementing
    0.39
     payloads
    0.39
    POSITIVE LOGITS
    ㄆ
    0.43
    р
    0.42
     वगैरह
    0.42
     тощо
    0.42
     և
    0.42
    その他の
    0.41
    щены
    0.40
     обору
    0.40
     возник
    0.40
     һәм
    0.40
    Activations Density 0.022%

    No Known Activations