© 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. 3597
    Prev
    Next
    INDEX
    Explanations

    code explanations and errors

    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
     Seen
    0.67
     Makes
    0.63
    Now
    0.63
     Compared
    0.62
    ゃ
    0.61
     벗
    0.61
     활동
    0.60
    They
    0.60
    Not
    0.60
     seen
    0.60
    POSITIVE LOGITS
     Imperial
    0.87
     imperial
    0.84
     interi
    0.79
     STANDARD
    0.78
     instrumentos
    0.78
     évaluations
    0.78
    <unused1887>
    0.78
     }^{*}$
    0.77
     intérieure
    0.77
     prothorace
    0.76
    Activations Density 0.020%

    No Known Activations