© 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. 4252
    Prev
    Next
    INDEX
    Explanations

    don't have and acquire

    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
    і
    1.28
    ی
    1.12
    ppure
    1.09
     Vertreter
    1.02
    ed
    1.01
     Email
    1.01
    gmail
    1.01
    代表
    1.00
    ת
    0.99
     représentants
    0.98
    POSITIVE LOGITS
     inertial
    1.26
     meson
    1.21
     `>=
    1.13
     spectrometers
    1.11
    ꯁ
    1.11
     beverages
    1.10
     computed
    1.10
     nourishing
    1.09
    (\\
    1.09
     nutritious
    1.08
    Activations Density 0.029%

    No Known Activations