© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1979
    Prev
    Next
    INDEX
    Explanations

    indicates or suggests

    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
    명을
    0.72
    名
    0.71
    ამო
    0.69
    名为
    0.68
     নামে
    0.65
     name
    0.65
    Named
    0.64
     முடிய
    0.64
    명
    0.63
     danh
    0.62
    POSITIVE LOGITS
     indicates
    2.16
     indicating
    2.15
     indicate
    2.09
     indicative
    1.94
     Indicates
    1.93
     indication
    1.89
     suggesting
    1.87
     suggests
    1.85
     indications
    1.81
     indicators
    1.80
    Activations Density 1.213%

    No Known Activations