© 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. 6484
    Prev
    Next
    INDEX
    Explanations

    words starting with r

    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
     बरत
    0.72
    হার
    0.70
    determined
    0.70
     चौ
    0.69
    Monitoring
    0.67
    뜨
    0.67
    ioen
    0.66
    Determ
    0.66
    }^{*}-
    0.66
    bathing
    0.65
    POSITIVE LOGITS
     Cran
    0.81
    omy
    0.81
    hetic
    0.80
     ucz
    0.79
    古
    0.78
     Casey
    0.77
     crown
    0.75
     developer
    0.75
     Kut
    0.75
    ify
    0.74
    Activations Density 0.039%

    No Known Activations