© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    even if errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     khoan
    1.07
    是很
    1.01
    PECT
    0.94
    OPT
    0.94
     Lhasa
    0.91
    眯
    0.91
    ATIVA
    0.88
     Pozn
    0.88
    是非常
    0.87
     aniline
    0.86
    POSITIVE LOGITS
     wins
    1.32
     Mascul
    1.28
    ian
    1.28
    ików
    1.27
     win
    1.26
     churn
    1.25
    ników
    1.23
    式
    1.21
     single
    1.20
     racking
    1.18
    Activations Density 0.079%

    No Known Activations