© 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. 11698
    Prev
    Next
    INDEX
    Explanations

    explaining systems and concepts

    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
    e
    1.47
    ہیں
    1.40
     націона
    1.36
    jų
    1.34
    ън
    1.33
    ecc
    1.33
    Watched
    1.32
    screw
    1.32
     mimetype
    1.31
    ය
    1.28
    POSITIVE LOGITS
     devra
    1.60
     poderá
    1.41
    ર્ચ
    1.38
     balle
    1.38
     alcance
    1.38
     caráter
    1.36
     darf
    1.35
     agot
    1.32
     llegará
    1.31
     enfrent
    1.30
    Activations Density 0.000%

    No Known Activations