© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12899
    Prev
    Next
    INDEX
    Explanations

    something or somethings

    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
    gris
    3.00
    ての
    2.88
    capt
    2.86
    canal
    2.84
    て
    2.83
    ozzi
    2.83
    які
    2.81
    carbonate
    2.77
    gers
    2.75
    onato
    2.73
    POSITIVE LOGITS
    s
    2.73
    س
    2.69
    ل
    2.59
    ن
    2.55
    тріш
    2.53
    ació
    2.46
    на
    2.44
    ശു
    2.44
    всем
    2.37
    いる
    2.34
    Activations Density 0.016%

    No Known Activations