© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9698
    Prev
    Next
    INDEX
    Explanations

    network port numbers and server programming

    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
    💡
    2.85
     EditText
    2.67
     padded
    2.55
    ತ್ಮ
    2.53
     сообщает
    2.51
     ImportError
    2.49
     tao
    2.46
     хотели
    2.46
     tenfold
    2.45
    ங்கிணை
    2.45
    POSITIVE LOGITS
    ت
    3.83
    efeuille
    3.76
    फोल
    3.31
    <0x80>
    3.29
    fö
    3.22
    RAIT
    2.98
    efeu
    2.95
    t
    2.94
    تين
    2.91
    ting
    2.91
    Activations Density 0.056%

    No Known Activations