Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47216
    Prev
    Next
    INDEX
    Explanations

    taking down, turn out

    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_17_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
    teilt
    1.35
     След
    1.24
     거죠
    1.23
    стве
    1.22
    erà
    1.20
    ції
    1.19
    finden
    1.17
    紝
    1.14
    újo
    1.14
    termine
    1.14
    POSITIVE LOGITS
    なかなか
    1.12
    м
    1.12
     Hair
    1.12
     hair
    1.09
     only
    1.07
     पथ
    1.05
     nun
    1.04
    োর
    1.03
    曾
    1.02
     entry
    1.01
    Activations Density 0.000%

    No Known Activations