© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3197
    Prev
    Next
    INDEX
    Explanations

    updating software and systems

    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_13_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
     यंदा
    0.89
     পী
    0.88
     pré
    0.82
     Barat
    0.82
    堅
    0.81
     ಇನ್ನೂ
    0.80
     relaunch
    0.80
    innie
    0.79
    藹
    0.79
     bimod
    0.79
    POSITIVE LOGITS
     opportunities
    0.66
     Empower
    0.66
     every
    0.65
     completing
    0.64
     Advancement
    0.63
     Информация
    0.63
    citizens
    0.62
     Improve
    0.62
    বৃত্ত
    0.61
     Opportunities
    0.60
    Activations Density 0.062%

    No Known Activations