© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    user interface commands

    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
     సినిమా
    0.67
    Aq
    0.66
     gravel
    0.66
    ור
    0.64
    ą
    0.64
     Cane
    0.64
     cane
    0.63
    ow
    0.63
     моче
    0.62
    狷
    0.62
    POSITIVE LOGITS
     right
    0.91
    right
    0.80
    Right
    0.76
     berichtet
    0.75
     Right
    0.73
    rieben
    0.71
     étude
    0.70
     klingt
    0.69
     markt
    0.67
     rechten
    0.66
    Activations Density 0.088%

    No Known Activations