© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4334
    Prev
    Next
    INDEX
    Explanations

    javascript code blocks

    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
     Prz
    0.79
    الع
    0.76
    אַ
    0.74
    Bed
    0.73
    }^{\
    0.72
    踰
    0.72
     Vries
    0.71
     Beds
    0.71
    ْم
    0.71
    내는
    0.71
    POSITIVE LOGITS
     Archim
    0.78
     recycling
    0.77
     =>
    0.75
     mindfulness
    0.74
     cortisol
    0.73
     Mandal
    0.72
     small
    0.70
     spinners
    0.68
     proprio
    0.68
     for
    0.67
    Activations Density 0.022%

    No Known Activations