© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148592
    Prev
    Next
    INDEX
    Explanations

    femtosecond pulse, impact resistant

    np_acts-logits-general · gemini-2.5-flash-lite

    instruction writes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Deux
    0.60
    Ann
    0.49
    ush
    0.47
    ();
    0.46
    Go
    0.46
    Bonjour
    0.45
    @
    0.45
    Je
    0.45
    Gh
    0.45
    Mus
    0.45
    POSITIVE LOGITS
     до
    0.54
     максима
    0.54
    setMaximum
    0.51
     макси
    0.48
     બા
    0.47
     ಸರಿಯ
    0.46
     нуле
    0.45
     запре
    0.45
     ство
    0.45
     чи
    0.44
    Activations Density 0.000%

    No Known Activations