© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 80
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    훤
    0.99
    샅
    0.89
    倔
    0.86
    وح
    0.82
     coarsely
    0.82
    ೂರು
    0.82
    建て
    0.81
    낡
    0.81
    秃
    0.81
     vieille
    0.80
    POSITIVE LOGITS
     effects
    3.32
     effect
    3.29
     impact
    2.96
    effects
    2.94
     Effects
    2.93
     Effect
    2.91
     impacts
    2.87
    Effects
    2.81
     consequences
    2.79
     benefits
    2.79
    Activations Density 4.195%

    No Known Activations