© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    model

    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
     Handwritten
    0.69
    我可以
    0.60
     strict
    0.58
     Strict
    0.58
     resveratrol
    0.58
     응
    0.58
    ekyll
    0.58
    才会
    0.57
    icates
    0.57
     麻
    0.56
    POSITIVE LOGITS
    Coming
    0.93
    Also
    0.92
    Another
    0.87
    Additionally
    0.76
    Auch
    0.76
    Beacon
    0.76
     आल्सो
    0.75
    Loving
    0.75
    Anyways
    0.75
    Again
    0.75
    Activations Density 0.090%

    No Known Activations