© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

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

    inherently a religion of violence

    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
    bildung
    0.41
     エ
    0.40
    ↵↵
    0.38
    エ
    0.37
    bild
    0.36
    section
    0.36
     ビ
    0.36
    <h2>
    0.35
    |
    0.35
     ノ
    0.35
    POSITIVE LOGITS
     stopwords
    0.36
     darwin
    0.36
     sacrificio
    0.35
    ৌশ
    0.34
    اتھن
    0.34
     ssl
    0.34
     foams
    0.34
     stirs
    0.34
    ᚑ
    0.34
     cancelar
    0.34
    Activations Density 0.001%

    No Known Activations