© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10568
    Prev
    Next
    INDEX
    Explanations

    defining speech

    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
    𝐞
    2.57
    𝐬
    2.53
    𝘀
    2.43
    醐
    2.40
     комму
    2.37
    és
    2.35
    ées
    2.30
    𝐨
    2.27
    iness
    2.24
    𝗲
    2.22
    POSITIVE LOGITS
    a
    3.99
    ه
    2.87
    此之外
    2.75
    া
    2.67
    ein
    2.64
    Quarter
    2.63
    oak
    2.57
    ו
    2.54
    o
    2.54
    нский
    2.50
    Activations Density 0.026%

    No Known Activations