© 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. 74929
    Prev
    Next
    INDEX
    Explanations

    prevent or person

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

    stories and travel

    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
    INGS
    0.44
    FolderPath
    0.42
    Certainly
    0.41
     сило
    0.40
    ين
    0.40
    Frequently
    0.40
    ﾅ
    0.39
     shavings
    0.38
    INUS
    0.38
     rocked
    0.38
    POSITIVE LOGITS
     amélior
    0.52
    𝚊
    0.50
     contraire
    0.49
     semblable
    0.49
     égaux
    0.48
     बदलाव
    0.48
    asamb
    0.48
     रझा
    0.48
     autonome
    0.47
     Koles
    0.47
    Activations Density 0.003%

    No Known Activations