© 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. 56320
    Prev
    Next
    INDEX
    Explanations

    needed format function capacity

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

    acknowledgement or capacity for something

    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
    reiro
    0.46
    eback
    0.44
    ｳ
    0.44
    accus
    0.44
    nicki
    0.44
    vich
    0.42
    aminated
    0.42
     أوروب
    0.42
     উল
    0.41
     ஓர்
    0.41
    POSITIVE LOGITS
    ,...
    0.48
     healers
    0.48
     sustent
    0.47
     trinity
    0.45
     phil
    0.45
     dexterity
    0.45
     guild
    0.45
    :...
    0.45
     pha
    0.45
     fetish
    0.45
    Activations Density 0.000%

    No Known Activations