© 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. 43270
    Prev
    Next
    INDEX
    Explanations

    Google products, higher levels, low group, clog pores

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

    bullet points and headings

    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
     иной
    0.55
     totality
    0.52
     shamb
    0.52
     deprive
    0.49
     ಅಭ
    0.48
     wretched
    0.48
    ᱟ
    0.47
     κι
    0.47
     exuber
    0.47
     मिमी
    0.47
    POSITIVE LOGITS
    建設
    0.50
    orov
    0.46
    働
    0.46
    ئ
    0.45
    هم
    0.44
     Genetic
    0.44
    Las
    0.44
     Galile
    0.44
     THEM
    0.43
    elas
    0.43
    Activations Density 0.000%

    No Known Activations