© 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. 2282
    Prev
    Next
    INDEX
    Explanations

    K, Kart, Kaggle, Kanjeevaram

    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
    вча
    3.67
    ൃത്ത
    3.54
    ulfill
    3.41
    houettes
    3.35
    rically
    3.32
    ières
    3.26
     acon
    3.26
    璿
    3.23
    <unused696>
    3.23
    amientos
    3.21
    POSITIVE LOGITS
    Dik
    2.64
    ﻢ
    2.60
     gek
    2.50
     K
    2.46
    젬
    2.46
     kor
    2.44
    ፍተኛ
    2.41
     kat
    2.40
     KER
    2.39
     ko
    2.38
    Activations Density 0.796%

    No Known Activations