© 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. 12302
    Prev
    Next
    INDEX
    Explanations

    Burj Khalifa, V-Bucks

    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
    en
    3.50
    ać
    3.41
    enal
    3.27
    enka
    3.26
    e
    3.20
    aard
    3.18
    esinin
    3.13
    ి
    3.07
    ei
    3.01
    enb
    2.93
    POSITIVE LOGITS
    rrrr
    2.86
    rrr
    2.78
    nan
    2.78
    side
    2.77
    ng
    2.71
    shots
    2.71
    녕하십니까
    2.69
    smith
    2.64
    ১২
    2.64
    ties
    2.64
    Activations Density 0.000%

    No Known Activations