© 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. 22-GEMMASCOPE-2-RES-16K
    7. 692
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    I
    0.48
    C
    0.48
    ↵↵
    0.46
    А
    0.43
    H
    0.43
    а
    0.42
    Y
    0.42
    ი
    0.41
    스
    0.41
    е
    0.41
    POSITIVE LOGITS
     their
    1.07
     those
    0.97
     these
    0.88
     THEIR
    0.81
     some
    0.78
     the
    0.78
     our
    0.76
     both
    0.76
     what
    0.75
     its
    0.75
    Activations Density 4.737%

    No Known Activations