© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7304
    Prev
    Next
    INDEX
    Explanations

    towards

    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
    över
    0.97
     Reap
    0.96
    एट
    0.94
     ABOVE
    0.89
    场合
    0.88
     Sold
    0.87
     Cutler
    0.86
    驒
    0.86
     IMPACT
    0.86
     STAND
    0.85
    POSITIVE LOGITS
     toward
    1.52
     towards
    1.45
     charted
    1.42
     paved
    1.40
     mapa
    1.31
     map
    1.29
     Richtung
    1.29
    towards
    1.28
     richting
    1.28
     directions
    1.27
    Activations Density 0.198%

    No Known Activations