© 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. 49325
    Prev
    Next
    INDEX
    Explanations

    cold brew

    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
     condemned
    0.41
    ۇل
    0.41
     представлены
    0.40
     bargains
    0.40
    ્વાસ
    0.39
     alienated
    0.38
    貘
    0.38
    ником
    0.37
    তিক্রম
    0.37
     باسکٹ
    0.37
    POSITIVE LOGITS
    gaard
    0.42
     mom
    0.41
     Cz
    0.40
    moment
    0.39
    4
    0.39
     Moment
    0.39
     Lack
    0.38
    chauff
    0.38
     तीव्रता
    0.38
     Daddy
    0.37
    Activations Density 0.012%

    No Known Activations