© 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. 90936
    Prev
    Next
    INDEX
    Explanations

    describes "mostly"

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

    leaving behind

    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
    Negative Logits
    League
    0.52
    adaki
    0.51
    ját
    0.50
    𝔬
    0.50
    affiliated
    0.48
    aná
    0.47
    apikey
    0.47
    asang
    0.47
    Unique
    0.47
    '_{
    0.46
    POSITIVE LOGITS
     impulso
    0.49
     dann
    0.47
     programa
    0.46
     Mostly
    0.46
    缛
    0.45
     problema
    0.45
     alunos
    0.44
     Maureen
    0.44
     Reactors
    0.44
     students
    0.44
    Activations Density 0.006%

    No Known Activations