© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43298
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evil
    0.47
     inflammation
    0.41
     insidious
    0.41
     prophylactic
    0.40
     norepinephrine
    0.40
    ?
    0.40
     homeostasis
    0.40
     phổi
    0.40
    肠
    0.40
     healing
    0.39
    POSITIVE LOGITS
     classiques
    0.49
    bmp
    0.47
     aveva
    0.47
     permette
    0.45
     Gregor
    0.45
     zarówno
    0.44
     precedenti
    0.44
     interess
    0.43
     permettent
    0.43
     Respondents
    0.43
    Activations Density 0.010%

    No Known Activations