© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    closing program block

    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
    "?>
    0.75
    颞
    0.74
     pouvait
    0.69
    DF
    0.68
     &=&
    0.68
     চলা
    0.67
    "></
    0.66
    entarios
    0.65
    प्रिंट
    0.64
    Implementation
    0.64
    POSITIVE LOGITS
     coming
    0.73
     hates
    0.69
     increasing
    0.69
     liked
    0.67
     earned
    0.67
     ଯ
    0.67
     hated
    0.64
     loved
    0.64
     incomplete
    0.64
     offering
    0.63
    Activations Density 0.082%

    No Known Activations