© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33292
    Prev
    Next
    INDEX
    Explanations

    driver assistance and safety systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itzar
    -1.34
     maravillosas
    -1.28
     necesitan
    -1.21
    ujuk
    -1.20
     Bemerkungen
    -1.18
    ᾷ
    -1.15
    ország
    -1.15
     podrían
    -1.14
     antiguo
    -1.14
     hermosas
    -1.13
    POSITIVE LOGITS
     verko
    1.32
    sividad
    1.21
     年级
    1.18
     赤ちゃん
    1.17
    gradable
    1.14
     کنید
    1.10
    ostro
    1.08
    フォル
    1.08
     Assist
    1.06
     namen
    1.06
    Activations Density 0.013%

    No Known Activations