© 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. 19860
    Prev
    Next
    INDEX
    Explanations

    various [type of noun]

    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
    an
    1.98
    า
    1.66
    to
    1.41
    FILE
    1.35
    Certain
    1.34
    quele
    1.28
    ان
    1.28
    ε
    1.27
    the
    1.26
    م
    1.24
    POSITIVE LOGITS
     macam
    2.43
     incarnations
    1.88
     iterations
    1.70
     stages
    1.45
     meats
    1.43
     soorten
    1.41
    各
    1.38
    qar
    1.37
     degrees
    1.35
     amounts
    1.34
    Activations Density 0.026%

    No Known Activations