© 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-16K
    7. 12569
    Prev
    Next
    INDEX
    Explanations

    J words

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

    other fruits or costly wars

    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_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
    насти
    0.51
    Biden
    0.47
    ारी
    0.45
    ཋ
    0.45
    DomainMask
    0.45
     perc
    0.44
    窕
    0.44
    tä
    0.44
     banget
    0.44
    殡
    0.44
    POSITIVE LOGITS
     schizophrenia
    0.52
     Ill
    0.52
     Colored
    0.52
     conjugates
    0.52
     B
    0.50
     Mixtures
    0.50
     hologram
    0.48
     V
    0.48
     VII
    0.48
     kanamycin
    0.48
    Activations Density 0.000%

    No Known Activations