© 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. 9993
    Prev
    Next
    INDEX
    Explanations

    fantasies, scenarios, emotions

    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
    ंटा
    0.93
    ه
    0.92
     யான
    0.88
    نات
    0.84
    पति
    0.83
    गल
    0.83
    મિ
    0.82
    هي
    0.82
    बल
    0.82
     wówczas
    0.82
    POSITIVE LOGITS
     throttle
    1.16
    throttle
    1.12
    oinette
    1.12
    inental
    1.07
    ti
    1.06
    грам
    1.05
    檛
    1.03
    ラル
    1.01
    t
    1.01
    ucky
    0.99
    Activations Density 0.080%

    No Known Activations