© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14148
    Prev
    Next
    INDEX
    Explanations

    significantly faster, perfectly outlined

    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_13_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
     amended
    2.08
    ्यादा
    1.99
    ျေး
    1.97
     considered
    1.91
    𝚘
    1.85
     reached
    1.79
     এছাড়া
    1.78
     Selective
    1.74
     categ
    1.73
     attended
    1.73
    POSITIVE LOGITS
    Ỷ
    2.16
    포
    1.84
    ชาว
    1.83
    뚤
    1.77
    To
    1.74
    ದಲು
    1.70
    下来
    1.69
    Formats
    1.68
    ದುಕ
    1.68
    unan
    1.68
    Activations Density 0.000%

    No Known Activations