© 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. 11907
    Prev
    Next
    INDEX
    Explanations

    Compute Unified Device Architecture (CUDA) and education

    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
    btnLogin
    2.08
    oksatta
    2.07
    AIR
    1.94
    蜴
    1.93
    atiya
    1.93
    сне
    1.88
    čet
    1.87
    žití
    1.86
    ärer
    1.86
    śc
    1.85
    POSITIVE LOGITS
    tive
    2.66
    a
    2.44
    н
    2.28
     Consecutive
    2.23
    tions
    2.14
    нні
    2.10
    బాద్
    2.06
     முடியவில்லை
    2.06
    radas
    2.05
    Length
    2.03
    Activations Density 0.016%

    No Known Activations