© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29727
    Prev
    Next
    INDEX
    Explanations

    Assault weapons, rings, climate, harm

    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_40_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
     Meanwhile
    0.42
     אחרי
    0.42
     Denote
    0.41
     مِنْ
    0.41
    Meanwhile
    0.40
     outro
    0.40
    嚆
    0.40
    ᵚ
    0.39
     继续
    0.39
     Porém
    0.39
    POSITIVE LOGITS
    ऊदी
    0.41
     anatomy
    0.38
     caution
    0.37
     hazards
    0.37
    adhan
    0.35
     geography
    0.35
    裄
    0.34
     trusts
    0.34
     rallies
    0.34
    चित्र
    0.33
    Activations Density 0.000%

    No Known Activations