© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70190
    Prev
    Next
    INDEX
    Explanations

    Talent and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    1.17
    rist
    1.07
    s
    1.06
    site
    0.97
     best
    0.95
     Pop
    0.94
     pra
    0.94
     pop
    0.92
     vill
    0.91
     ce
    0.91
    POSITIVE LOGITS
    ifizieren
    2.22
    oksatta
    2.09
     holen
    1.98
    getMaster
    1.94
    𝓼
    1.93
    entwicklung
    1.92
    elligence
    1.90
    﨑
    1.90
     dailySales
    1.90
     setNew
    1.89
    Activations Density 0.000%

    No Known Activations