© 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. 10200
    Prev
    Next
    INDEX
    Explanations

    crisis hotlines

    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
     becoming
    0.92
     became
    0.89
     fullname
    0.86
    ይ
    0.84
    fasterxml
    0.84
     chromospheres
    0.82
     comprehension
    0.81
     setae
    0.81
     নেতৃত্বের
    0.80
    本身的
    0.80
    POSITIVE LOGITS
     ਵੱ
    0.99
     কর্তৃক
    0.87
     zab
    0.86
     χρη
    0.85
     свър
    0.83
     ખૂ
    0.82
     以下
    0.81
    $<
    0.80
     توصیه
    0.79
     rekom
    0.79
    Activations Density 0.019%

    No Known Activations