© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    hair, color, and styles

    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
    orElse
    2.51
    ЛЕ
    2.33
     built
    2.12
     lean
    2.11
     site
    2.11
     fortress
    2.09
    Regards
    2.09
    ℝ
    2.09
     plein
    2.06
    Lazy
    1.99
    POSITIVE LOGITS
    髻
    2.38
     haired
    2.35
    urlar
    2.28
    rawa
    2.18
    hairs
    2.18
    haired
    2.17
    묶
    2.17
    chein
    2.14
    ynia
    2.14
    undur
    2.11
    Activations Density 0.186%

    No Known Activations