© 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. 13-GEMMASCOPE-2-RES-16K
    7. 897
    Prev
    Next
    INDEX
    Explanations

    folder/projects/links

    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_13_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
    absorption
    1.43
    isomer
    1.39
    absorbed
    1.35
    commut
    1.29
    समय
    1.28
    isot
    1.27
    ޘ
    1.27
    smoked
    1.26
    injection
    1.26
    saturation
    1.24
    POSITIVE LOGITS
     的
    1.99
     在
    1.66
     に
    1.60
     の
    1.58
     에서
    1.55
     에
    1.50
     大
    1.47
     地
    1.45
    에서
    1.37
     是
    1.37
    Activations Density 0.300%

    No Known Activations