© 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-65K
    7. 1318
    Prev
    Next
    INDEX
    Explanations

    broken down into

    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_65k_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
    ial
    1.72
    elf
    1.46
    ة
    1.46
    ization
    1.42
    ek
    1.39
    তা
    1.36
    wick
    1.35
    await
    1.32
    ма
    1.32
    ️
    1.30
    POSITIVE LOGITS
    汅
    1.73
    ꗥ
    1.71
    ᚗ
    1.70
    Ⴚ
    1.68
    뷌
    1.67
    ꩡ
    1.66
    쳏
    1.66
    꾻
    1.66
    <unused832>
    1.65
    껿
    1.64
    Activations Density 0.377%

    No Known Activations