© 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. 2499
    Prev
    Next
    INDEX
    Explanations

    Spanish, French, Chinese cues

    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
    basecode
    2.96
     [{"
    2.78
    𝓸
    2.63
    𝓲
    2.60
    utm
    2.53
    ్యూ
    2.48
    izedBox
    2.46
    বারে
    2.41
    벤트
    2.39
     *"
    2.37
    POSITIVE LOGITS
    ۲
    3.13
    e
    3.02
    ský
    2.92
    רות
    2.91
    ské
    2.90
    ी
    2.89
    ा
    2.87
    𝑒
    2.83
    ević
    2.82
    การ
    2.82
    Activations Density 0.734%

    No Known Activations