© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149350
    Prev
    Next
    INDEX
    Explanations

    after 'for'

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

    parenthetical comments or clauses

    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
     (
    0.53
     match
    0.48
     cartoons
    0.48
     excerpts
    0.48
     cartoon
    0.48
     highlights
    0.47
     podcasts
    0.47
     resource
    0.46
     podcast
    0.46
     poetic
    0.45
    POSITIVE LOGITS
    হিন্দু
    0.56
    THEOREM
    0.52
    ângulo
    0.50
    ш
    0.49
    ње
    0.49
     njeg
    0.49
    importanza
    0.48
    âge
    0.48
    Ⴚ
    0.48
    Пред
    0.47
    Activations Density 0.001%

    No Known Activations