© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    expression for substitution

    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
    vskip
    1.34
    textcolor
    1.31
     trick
    1.26
    atribut
    1.26
    љено
    1.25
    ᅣ
    1.22
    reactivex
    1.22
    壘
    1.22
    ᱫ
    1.20
    无可
    1.17
    POSITIVE LOGITS
    nya
    1.26
     proceso
    1.23
    lands
    1.17
     Lantern
    1.16
    woods
    1.14
     Command
    1.12
     कोल
    1.12
    OrEqualTo
    1.12
     gimana
    1.11
     Capital
    1.11
    Activations Density 0.121%

    No Known Activations