© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    hypothetical pasts and actions

    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
    ი
    4.01
    esini
    3.55
    es
    3.52
    یه
    3.43
    oing
    3.32
    ה
    3.26
    ে
    3.23
    ০
    3.20
    ی
    3.10
    ascular
    3.08
    POSITIVE LOGITS
    medskip
    2.26
    선
    2.23
    mehr
    2.17
    soon
    2.16
    otte
    2.16
    ized
    2.14
    lines
    2.13
    mail
    2.06
    appa
    2.01
    릉
    2.00
    Activations Density 0.009%

    No Known Activations