© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 362
    Prev
    Next
    INDEX
    Explanations

    list items with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    zinho
    0.90
    卡通
    0.87
    க்குக
    0.83
    นั้น
    0.83
     safety
    0.81
    ச்
    0.81
    撑
    0.79
    en
    0.78
     Safe
    0.78
     ungu
    0.77
    POSITIVE LOGITS
    }=$
    1.12
    footnotes
    1.10
     aspectos
    1.10
    died
    1.08
    .=
    1.04
     transforme
    1.03
     dissociate
    1.01
     conformément
    1.00
     reformulated
    1.00
    ˡ
    0.99
    Activations Density 0.000%

    No Known Activations