© 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-65K
    7. 48735
    Prev
    Next
    INDEX
    Explanations

    list item marker

    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_65k_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
     quarrels
    0.42
     emin
    0.41
     dom
    0.38
    4
    0.37
    9
    0.37
     nas
    0.37
     Quand
    0.37
    ismatch
    0.37
     smokes
    0.37
     sol
    0.37
    POSITIVE LOGITS
     అంటూ
    0.51
    ду
    0.47
     অবশেষে
    0.44
    全面的
    0.44
     കൂടുതൽ
    0.44
    大切な
    0.44
     そして
    0.43
     రూపొ
    0.43
    泌
    0.42
    渴望
    0.42
    Activations Density 0.002%

    No Known Activations