© 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. 2372
    Prev
    Next
    INDEX
    Explanations

    NAMI mental health resources

    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
     gstlal
    0.44
    轢
    0.42
    Ⲉ
    0.42
    ONEDB
    0.39
    тельную
    0.39
     Therapie
    0.39
     copywriting
    0.39
    洴
    0.38
    ूहिक
    0.38
     perpetuity
    0.38
    POSITIVE LOGITS
     NIM
    0.45
     familiares
    0.42
     National
    0.41
     মায়ের
    0.41
     NATIONAL
    0.39
     schizophren
    0.38
     জাতীয়
    0.38
     encontrar
    0.38
     ভোট
    0.37
    Famil
    0.37
    Activations Density 0.004%

    No Known Activations