© 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
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7673
    Prev
    Next
    INDEX
    Explanations

    just a little bit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    フィール
    0.87
    oine
    0.84
    ymen
    0.81
    bedo
    0.80
    ライダー
    0.79
    isLoading
    0.79
    zac
    0.78
    浮
    0.77
    immediately
    0.75
    ვე
    0.74
    POSITIVE LOGITS
     past
    1.27
     PAST
    1.25
    past
    1.13
     Past
    1.09
     succesfully
    1.04
     successfully
    0.99
    Past
    0.98
     halfway
    0.94
     sampai
    0.94
     ¼
    0.92
    Activations Density 0.111%

    No Known Activations