© 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. 260
    Prev
    Next
    INDEX
    Explanations

    marines

    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
     antecedent
    0.88
     maked
    0.79
     compulsion
    0.76
     perplexing
    0.75
     CONSIDER
    0.75
    逢
    0.73
     einf
    0.72
    RESOL
    0.71
     complementarity
    0.71
     malad
    0.70
    POSITIVE LOGITS
    oa
    1.15
    édia
    0.98
    ensis
    0.97
    chia
    0.95
    loa
    0.89
    ਾ
    0.89
    aya
    0.88
    kka
    0.87
    ỏ
    0.86
    ia
    0.86
    Activations Density 1.683%

    No Known Activations