© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    What makes you unique

    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
    ي
    4.03
    y
    3.35
    yth
    2.89
    ing
    2.80
    ic
    2.76
    يلي
    2.70
    り
    2.67
    dehyde
    2.67
    ત્મ
    2.67
    yya
    2.66
    POSITIVE LOGITS
    preset
    2.59
    𝘦
    2.56
     সংখ্যক
    2.53
    сног
    2.51
    𝘢
    2.49
    ository
    2.42
     主要
    2.40
    েন্সি
    2.40
    Couple
    2.39
    ees
    2.37
    Activations Density 0.117%

    No Known Activations