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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3288
    Prev
    Next
    INDEX
    Explanations

    original skin. irritation

    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
    frames
    3.02
     میری
    2.76
    थि
    2.63
    cki
    2.57
    要
    2.56
     recesses
    2.54
    शुदा
    2.53
    FolderPath
    2.51
     sacraments
    2.50
    ğinden
    2.50
    POSITIVE LOGITS
    s
    4.76
    ের
    4.31
    ০
    3.16
    র
    3.11
    ي
    3.10
    ات
    3.06
    ર
    2.94
    𝓷
    2.92
    HING
    2.88
    ों
    2.74
    Activations Density 0.232%

    No Known Activations