© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199360
    Prev
    Next
    INDEX
    Explanations

    conservatives apologized

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

    choices A, B, C, or D

    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
    ми
    0.54
     сма
    0.51
     б
    0.48
    šit
    0.48
     стабили
    0.47
     стаби
    0.46
     т
    0.46
     шу
    0.46
    т
    0.45
     requisite
    0.45
    POSITIVE LOGITS
     restor
    0.48
    GER
    0.46
     ny
    0.46
    Resume
    0.45
     abortions
    0.45
     സം
    0.45
     paragraphs
    0.45
     loob
    0.45
    PAGE
    0.44
    Abort
    0.44
    Activations Density 0.001%

    No Known Activations