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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4150
    Prev
    Next
    INDEX
    Explanations

    function definitions with return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     procent
    0.66
     많
    0.63
     éve
    0.63
    될
    0.61
     subtitles
    0.61
     much
    0.58
    減
    0.57
     there
    0.57
    ঃখ
    0.56
     percent
    0.55
    POSITIVE LOGITS
    ➜
    0.90
     ไง
    0.88
     ين
    0.87
     በሚ
    0.86
     BABY
    0.86
     Baby
    0.83
     Stranger
    0.82
    Baby
    0.81
    द्योगिकी
    0.81
    ⏩
    0.80
    Activations Density 0.068%

    No Known Activations