© 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. 17-GEMMASCOPE-2-RES-16K
    7. 8820
    Prev
    Next
    INDEX
    Explanations

    specializing or focused on

    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_17_width_16k_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
     Kanji
    0.72
    removeAttr
    0.71
     lovely
    0.71
     gorgeous
    0.67
    讧
    0.67
    ‍♂️
    0.65
    genommen
    0.65
     bagus
    0.65
     redhead
    0.64
     afterlife
    0.64
    POSITIVE LOGITS
     ________
    2.10
     _______
    1.98
     ____________
    1.92
     ______
    1.88
     __________
    1.87
     _____
    1.78
     ____
    1.77
    _______
    1.77
    ________
    1.67
     _____________
    1.67
    Activations Density 0.238%

    No Known Activations