© 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-262K
    7. 14881
    Prev
    Next
    INDEX
    Explanations

    Popularity

    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_22_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
    ellipse
    1.46
    도
    1.43
    aura
    1.41
    如果您
    1.40
    thed
    1.34
    ので
    1.34
    aes
    1.32
    ることができます
    1.30
    া
    1.27
     リン
    1.26
    POSITIVE LOGITS
    ization
    1.72
    ity
    1.60
    ন
    1.58
    izing
    1.54
    ised
    1.46
    ising
    1.37
    ität
    1.36
    ied
    1.32
    izes
    1.31
    izations
    1.30
    Activations Density 0.023%

    No Known Activations