© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2777
    Prev
    Next
    INDEX
    Explanations

    sp, spar, or space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ಲ
    0.60
    leon
    0.57
    El
    0.56
    اسی
    0.55
    μί
    0.55
    ᅳ
    0.55
     Hid
    0.55
    氀
    0.54
    eln
    0.54
    لات
    0.54
    POSITIVE LOGITS
    sp
    0.84
    SP
    0.78
     спа
    0.77
    スパ
    0.75
    spel
    0.75
     Spear
    0.72
    MTAB
    0.71
     Sparks
    0.70
     SP
    0.70
    ទ្
    0.69
    Activations Density 0.157%

    No Known Activations