© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7786
    Prev
    Next
    INDEX
    Explanations

    technical terms and foreign languages

    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_13_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
     devastating
    1.28
    垩
    1.20
     struggle
    1.16
    鉋
    1.16
     damning
    1.12
    ライプ
    1.11
     loadings
    1.10
    ంచ్
    1.09
     消
    1.08
     фундамента
    1.08
    POSITIVE LOGITS
    nickname
    1.36
     vende
    1.16
     biri
    1.11
    telefono
    1.09
     nickname
    1.08
    bibli
    1.07
     Permission
    1.07
     nome
    1.07
     fez
    1.07
     visited
    1.06
    Activations Density 0.000%

    No Known Activations