© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14490
    Prev
    Next
    INDEX
    Explanations

    very + fundamental essence

    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_7_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
    n
    3.43
    r
    2.95
    ン
    2.82
    nig
    2.80
    ་
    2.70
    nW
    2.51
    m
    2.49
    ו
    2.47
    mese
    2.46
    l
    2.45
    POSITIVE LOGITS
    ech
    2.60
    glers
    2.46
    drig
    2.41
    playSound
    2.40
    eh
    2.36
    ỷ
    2.35
    jení
    2.28
    dirs
    2.19
    jsk
    2.19
    स्कूल
    2.15
    Activations Density 0.030%

    No Known Activations