© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    cannot fulfill requests

    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
     kimono
    0.74
     ponencia
    0.67
    DEPTH
    0.65
    oprene
    0.63
    dumps
    0.63
     लेकर
    0.63
    =['
    0.63
    toHaveBeenCalled
    0.62
    ദ
    0.62
    inho
    0.62
    POSITIVE LOGITS
     Certified
    0.65
    "?
    0.64
    ardino
    0.64
     minimizes
    0.62
    疏
    0.61
     никто
    0.61
     every
    0.60
    вий
    0.60
     evita
    0.60
     directo
    0.59
    Activations Density 0.120%

    No Known Activations