© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10174
    Prev
    Next
    INDEX
    Explanations

    Python class initialization

    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
     여
    0.98
     член
    0.98
    根
    0.97
    /__
    0.92
    /-
    0.91
    vnd
    0.91
    gulation
    0.91
     कमेटी
    0.89
     /
    0.88
    srand
    0.86
    POSITIVE LOGITS
     many
    1.62
    many
    1.60
     MANY
    1.39
     deal
    1.39
    Many
    1.36
    MANY
    1.32
     muitos
    1.30
     banyak
    1.29
     tanti
    1.29
     muchos
    1.27
    Activations Density 0.100%

    No Known Activations