© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    data and memory storage

    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
    Ы
    2.71
    develop
    2.50
    TE
    2.35
    𝗺
    2.32
    𝗼
    2.31
    AE
    2.31
    sembl
    2.27
     serializer
    2.24
    ヤー
    2.24
    蟆
    2.23
    POSITIVE LOGITS
    ו
    4.53
    a
    3.25
    i
    3.17
    ු
    3.14
    า
    3.10
    고
    3.06
    াৰ
    2.93
    া
    2.92
    u
    2.86
    iul
    2.81
    Activations Density 0.098%

    No Known Activations