© 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. 8255
    Prev
    Next
    INDEX
    Explanations

    aiming for a specific outcome

    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
     Undo
    0.90
    슨
    0.90
    ଂ
    0.83
    ूफ
    0.82
     Frum
    0.82
     zoon
    0.82
    ಮಿ
    0.81
     xem
    0.80
    튬
    0.79
    裟
    0.79
    POSITIVE LOGITS
    lessly
    1.08
    няется
    0.86
    net
    0.85
    higher
    0.82
    aktadır
    0.80
    setting
    0.79
    Direct
    0.79
    graduate
    0.79
     toward
    0.78
    direct
    0.78
    Activations Density 0.045%

    No Known Activations