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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3401
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific verbs/adjectives

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

    likewise, similar

    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_53_width_65k_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
    御座
    0.38
    躡
    0.35
    㞓
    0.34
     ocasiones
    0.34
    意的
    0.34
    ύν
    0.34
    कोई
    0.33
    Ꮫ
    0.33
     গ্রহণ
    0.33
    合理的
    0.33
    POSITIVE LOGITS
     Zuck
    0.36
     ‬
    0.35
    ™
    0.34
     ის
    0.33
    ️
    0.33
     worldRank
    0.31
     అందుకే
    0.31
     −/−
    0.31
     thisStudent
    0.31
     unsurprisingly
    0.30
    Activations Density 0.922%

    No Known Activations