© 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. 5232
    Prev
    Next
    INDEX
    Explanations

    cobblestone streets and syncopated rhythms

    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
    狼
    0.63
     hypnot
    0.61
    products
    0.61
    皋
    0.61
     psychologically
    0.60
    Ratio
    0.60
     gatos
    0.59
     shampoos
    0.59
     proclamation
    0.59
     drugs
    0.58
    POSITIVE LOGITS
    ind
    0.66
     numb
    0.61
     છો
    0.58
    num
    0.58
    ک
    0.58
     Towards
    0.57
    飛ば
    0.56
    여
    0.56
    istä
    0.55
    backslash
    0.55
    Activations Density 0.123%

    No Known Activations