© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     down
    0.69
     into
    0.67
     bij
    0.65
     quelqu
    0.64
     tribal
    0.64
     非
    0.64
                                   
    0.63
    角色
    0.63
    occasione
    0.63
                          
    0.63
    POSITIVE LOGITS
    ore
    0.72
    綜合
    0.71
     concluded
    0.71
    แพ
    0.68
    ියේ
    0.67
    including
    0.66
    ORE
    0.66
     ಮಟ್ಟ
    0.66
    മതി
    0.65
     Сле
    0.65
    Activations Density 0.058%

    No Known Activations