© 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. 6930
    Prev
    Next
    INDEX
    Explanations

    provides for support

    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
     -
    1.42
     --
    1.27
     –
    1.27
    itee
    1.12
     ---
    1.11
     -,
    1.08
    liest
    1.06
     —
    1.05
     -"
    1.03
     -=
    1.03
    POSITIVE LOGITS
    -
    1.37
    ‑
    0.97
    னால்
    0.90
    
    0.83
     말고
    0.82
    -|
    0.81
     nämlich
    0.79
    -${
    0.76
    ‮
    0.76
    -}
    0.75
    Activations Density 0.151%

    No Known Activations