© 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. 22-GEMMASCOPE-2-RES-16K
    7. 5541
    Prev
    Next
    INDEX
    Explanations

    purpose or relation for

    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_22_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
    ազ
    0.82
    勎
    0.78
     விய
    0.77
    堹
    0.76
    Bas
    0.74
     Stabilization
    0.74
    තා
    0.73
    StatusBadRequest
    0.71
    詷
    0.71
    玴
    0.70
    POSITIVE LOGITS
     Of
    1.30
    Of
    1.13
     To
    1.03
     For
    1.02
    To
    0.92
    For
    0.86
     OF
    0.85
    Towards
    0.84
     TO
    0.81
     Towards
    0.76
    Activations Density 0.169%

    No Known Activations