© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4371
    Prev
    Next
    INDEX
    Explanations

    complete loss of function

    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_13_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
     #
    0.70
     eril
    0.68
     diverso
    0.60
    ান
    0.60
     bertujuan
    0.59
    ley
    0.58
    #
    0.58
    antes
    0.57
    意外
    0.57
     Tuz
    0.55
    POSITIVE LOGITS
     sufficiency
    0.88
    enapi
    0.87
     vollständ
    0.86
     Grenze
    0.85
     거의
    0.84
    딪
    0.83
     saturation
    0.83
     майже
    0.83
     satiety
    0.83
    saturation
    0.82
    Activations Density 0.458%

    No Known Activations