© 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. 8073
    Prev
    Next
    INDEX
    Explanations

    Key explanations and improvements

    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
    🕺
    0.98
     Bootcamp
    0.98
    💃
    0.95
     leren
    0.95
    🎵
    0.94
    なんて
    0.94
    🎶
    0.94
    🏄
    0.94
    を作り
    0.94
    って
    0.93
    POSITIVE LOGITS
     paragra
    0.81
     be
    0.79
     ugy
    0.79
    vore
    0.76
     bekl
    0.74
     parag
    0.72
     bed
    0.71
     (§
    0.70
     attest
    0.69
     justific
    0.69
    Activations Density 0.004%

    No Known Activations