© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138955
    Prev
    Next
    INDEX
    Explanations

    including any or non

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

    often involving, not fully, blocking pain

    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
    𒄀
    0.53
    呥
    0.52
    طيب
    0.51
    ',\
    0.50
    /*',
    0.50
     〢
    0.50
    挕
    0.49
    .*/
    0.49
    ′,
    0.49
    바
    0.49
    POSITIVE LOGITS
     tot
    0.48
     cuddle
    0.45
    被告
    0.44
     coder
    0.44
     betas
    0.43
     colloid
    0.43
     Garda
    0.42
     totales
    0.42
     full
    0.42
     जिलों
    0.42
    Activations Density 0.001%

    No Known Activations