© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8554
    Prev
    Next
    INDEX
    Explanations

    user interface commands

    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_9_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
     choć
    1.00
     aunque
    0.92
     tenho
    0.85
     большинстве
    0.81
     obwohl
    0.81
     eram
    0.80
     같
    0.80
     miatt
    0.78
    вец
    0.78
     なん
    0.78
    POSITIVE LOGITS
    your
    0.96
    the
    0.92
     your
    0.82
     the
    0.82
    The
    0.81
    you
    0.72
    Europa
    0.72
    Your
    0.72
    ο
    0.72
     George
    0.72
    Activations Density 0.477%

    No Known Activations