© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3557
    Prev
    Next
    INDEX
    Explanations

    understanding the world

    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
    関数
    1.07
    函数
    0.98
     belirl
    0.98
    其
    0.98
     метод
    0.96
     denominado
    0.94
     یا
    0.93
     함수
    0.92
    ∪
    0.92
    ()));
    0.92
    POSITIVE LOGITS
    wood
    0.83
     guys
    0.73
     opinion
    0.72
    ming
    0.72
    ness
    0.71
    ung
    0.69
     amb
    0.69
     meet
    0.69
    town
    0.69
    kaya
    0.69
    Activations Density 0.000%

    No Known Activations