© 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. 114232
    Prev
    Next
    INDEX
    Explanations

    qualifying adjectives and connectives

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

    just allow

    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
     prolog
    0.46
     роки
    0.45
    詩
    0.45
    獄
    0.44
     immobil
    0.44
     applique
    0.43
     Коло
    0.43
     apparatus
    0.42
     atmosph
    0.42
    वालों
    0.42
    POSITIVE LOGITS
    ᴅ
    0.47
     पुनः
    0.46
    into
    0.46
    Ρ
    0.46
    Ý
    0.46
    ic
    0.45
     တစ်
    0.44
    within
    0.44
     bądź
    0.43
    Bước
    0.42
    Activations Density 0.004%

    No Known Activations