© 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. 20084
    Prev
    Next
    INDEX
    Explanations

    with a

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

    X with Y descriptor

    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
     считаю
    0.49
    糉
    0.41
    WinCounter
    0.39
     TComponent
    0.38
     Posterior
    0.37
    ۗ
    0.37
     Inspired
    0.37
     過
    0.37
     postérieur
    0.37
    ☄
    0.36
    POSITIVE LOGITS
     markings
    0.47
     affixed
    0.47
    mounted
    0.45
     thereon
    0.45
    Somebody
    0.43
     flanges
    0.42
     legs
    0.40
    den
    0.40
     отверсти
    0.40
     ruedas
    0.39
    Activations Density 0.086%

    No Known Activations