© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    cute and playful descriptions

    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
    nessy
    2.31
    locality
    2.28
    rough
    2.22
    ESCAPE
    2.20
    儡
    2.18
    觎
    2.12
    np
    2.11
    ivari
    2.10
    dise
    2.10
    vp
    2.08
    POSITIVE LOGITS
    ع
    3.14
    علم
    2.76
     previs
    2.71
    عاد
    2.65
    प्रेम
    2.63
    ্যোগ
    2.46
     sourire
    2.45
    oires
    2.43
    ালের
    2.43
    عرض
    2.41
    Activations Density 0.012%

    No Known Activations