© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1754
    Prev
    Next
    INDEX
    Explanations

    openai, GPT, TTS, ffmpeg, UTF, Potter

    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
     as
    1.81
     ショルダー
    1.70
     with
    1.69
    -
    1.69
     and
    1.67
     STEM
    1.60
     by
    1.60
    .
    1.60
     黃
    1.60
     that
    1.58
    POSITIVE LOGITS
    Sementara
    2.29
     relatório
    2.20
     voluntad
    2.19
    tidak
    2.13
     aniversário
    2.13
     passeio
    2.11
     layanan
    2.10
     benöt
    2.10
     ganancias
    2.10
     daño
    2.09
    Activations Density 0.374%

    No Known Activations