© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15017
    Prev
    Next
    INDEX
    Explanations

    start or begin actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    に使
    1.27
    OpenJDK
    1.18
    ⊹
    1.16
    ре
    1.14
    に来
    1.14
    度的
    1.13
    ない
    1.13
    ná
    1.10
    녕하세요
    1.10
    다고
    1.10
    POSITIVE LOGITS
    יים
    1.41
     anew
    1.13
    ோ
    1.11
    ębior
    1.08
     afresh
    1.07
    ാ
    1.07
    jų
    1.05
    odore
    1.02
    ar
    1.01
     outset
    1.01
    Activations Density 0.129%

    No Known Activations