© 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
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2760
    Prev
    Next
    INDEX
    Explanations

    leading in innovation and economics

    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
     Rules
    0.86
    ation
    0.83
    ं
    0.81
    攸
    0.71
     rule
    0.70
     rules
    0.69
    abl
    0.69
    upon
    0.68
    ಷ
    0.67
     Rule
    0.65
    POSITIVE LOGITS
    স্থানীয়
    1.19
    trasound
    1.12
    ERSHIP
    1.10
     astray
    1.07
    স্থানীয়
    1.07
    ileno
    0.99
     pensamento
    0.96
    IVATE
    0.96
     religieux
    0.95
     njia
    0.93
    Activations Density 0.102%

    No Known Activations