© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5743
    Prev
    Next
    INDEX
    Explanations

    impossibility and difficulty

    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
    ارين
    2.08
    系の
    2.01
     Вене
    1.86
    érg
    1.83
     Lately
    1.83
     Lamar
    1.82
    като
    1.80
    н
    1.77
    tamb
    1.77
     recently
    1.77
    POSITIVE LOGITS
     WITHOUT
    1.28
    FORE
    1.21
    without
    1.17
    ytoin
    1.16
    BACH
    1.12
     probabilities
    1.12
     delito
    1.12
     FORE
    1.10
    analyse
    1.09
     fără
    1.08
    Activations Density 0.056%

    No Known Activations