© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14612
    Prev
    Next
    INDEX
    Explanations

    Again,

    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
     redis
    1.63
     Po
    1.49
     Hare
    1.47
     actual
    1.44
     Pav
    1.42
     ay
    1.39
     w
    1.37
     Pr
    1.35
     Hal
    1.34
     Floating
    1.33
    POSITIVE LOGITS
    uniqueItems
    1.92
    endous
    1.86
    ersburg
    1.82
    aboo
    1.81
    蛋白質
    1.74
    omycin
    1.72
    oprotein
    1.72
    癥
    1.72
    ﺙ
    1.71
    electrolyte
    1.71
    Activations Density 0.052%

    No Known Activations