© 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. 112958
    Prev
    Next
    INDEX
    Explanations

    tissue culture, iOS, village, teenagers

    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
     matrimonio
    0.50
     dienen
    0.46
     બાળક
    0.44
    訢
    0.43
     dítě
    0.43
    لمين
    0.43
     diaria
    0.42
     iccad
    0.42
    𓐄
    0.42
     Alhamdulillah
    0.42
    POSITIVE LOGITS
    )
    0.61
    Vel
    0.60
    Interview
    0.54
    ing
    0.50
    :
    0.49
    я
    0.49
    Whether
    0.49
    Hugo
    0.48
    Telephone
    0.48
    ीट
    0.48
    Activations Density 0.000%

    No Known Activations