© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8404
    Prev
    Next
    INDEX
    Explanations

    resume or invoice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ή
    0.94
    ált
    0.90
     Gora
    0.89
    
    0.82
    reciate
    0.81
    iyim
    0.78
     Böyle
    0.77
     Unido
    0.77
    lear
    0.77
     Champs
    0.77
    POSITIVE LOGITS
    texto
    0.88
    Greece
    0.81
    唬
    0.78
    สั่ง
    0.78
     साल
    0.78
    documents
    0.78
    angry
    0.78
    Diagn
    0.77
    Sulf
    0.76
    ถูกต้อง
    0.75
    Activations Density 0.165%

    No Known Activations