© 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. 125523
    Prev
    Next
    INDEX
    Explanations

    government authority, seasonality, specific names

    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
    英国
    0.48
    ValMap
    0.40
     ਜਾ
    0.39
     bzw
    0.38
     विशेष
    0.38
    ५
    0.38
    ྛ
    0.38
    decimal
    0.38
     要
    0.38
    Ч
    0.38
    POSITIVE LOGITS
     Petersburg
    0.39
     mgr
    0.38
    ress
    0.38
     Reclamation
    0.38
     thải
    0.37
     GMC
    0.37
     Danville
    0.37
     insurmountable
    0.36
     జరిగ
    0.36
     постара
    0.36
    Activations Density 0.000%

    No Known Activations