© 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. 136282
    Prev
    Next
    INDEX
    Explanations

    adjective or adverb followed by continuation

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

    off the main

    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
     Zustimmung
    0.50
    <td>
    0.49
     s
    0.45
     ">
    0.43
    producer
    0.43
     প্রত্যাখ্যান
    0.42
    ipat
    0.42
    associated
    0.42
     zn
    0.42
    its
    0.40
    POSITIVE LOGITS
    ঞ্জ
    0.50
    仵
    0.48
    ंटे
    0.47
    प्रश्न
    0.46
    텃
    0.46
    봇
    0.45
    鸪
    0.45
    द्धांत
    0.45
    र्दू
    0.45
    ໆ
    0.45
    Activations Density 0.000%

    No Known Activations