© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    self-attention mechanism

    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
     giai
    1.51
    Roboto
    1.46
     nervioso
    1.44
     jarang
    1.41
    โอ
    1.39
    ㅉ
    1.37
    ल्ली
    1.36
    ́n
    1.35
    Pues
    1.34
    Unknown
    1.33
    POSITIVE LOGITS
    gies
    1.70
    是对
    1.63
    柜
    1.55
    احث
    1.52
    是對
    1.51
    лм
    1.50
    gery
    1.47
     পড়ার
    1.44
     Honours
    1.44
    رش
    1.42
    Activations Density 0.007%

    No Known Activations