© 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. 121544
    Prev
    Next
    INDEX
    Explanations

    after common words

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

    decisions, meaning, going, builds

    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
    🇾
    0.48
     шум
    0.47
    ють
    0.46
    écies
    0.44
     tronco
    0.44
    ;_
    0.43
     raged
    0.43
    até
    0.42
     aspecto
    0.42
     certamente
    0.42
    POSITIVE LOGITS
     अनु
    0.47
     കൂടുതൽ
    0.46
     педагоги
    0.46
     теория
    0.45
    縝
    0.44
     teoria
    0.43
     издели
    0.43
     तंत्र
    0.42
     होत्या
    0.42
     культура
    0.42
    Activations Density 0.001%

    No Known Activations