© 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. 7969
    Prev
    Next
    INDEX
    Explanations

    acknowledging potential situations

    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
    Pic
    0.88
    bur
    0.86
     RACE
    0.85
     Pip
    0.84
    ป์
    0.84
    риф
    0.83
     reass
    0.82
    염
    0.81
    Pip
    0.81
    had
    0.80
    POSITIVE LOGITS
    кция
    0.94
    シオ
    0.94
    スナー
    0.92
    ferences
    0.89
    aders
    0.89
    creatic
    0.89
    plica
    0.88
    шением
    0.88
    জিস্ট
    0.87
    ferencia
    0.86
    Activations Density 0.020%

    No Known Activations