© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78036
    Prev
    Next
    INDEX
    Explanations

    writing is difficult

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

    creative writing

    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
    Negative Logits
    к
    0.61
     Audiobook
    0.58
    г
    0.55
    де
    0.54
    𝙠
    0.54
    ش
    0.53
    س
    0.49
    𝗸
    0.48
    فیلم
    0.48
     audiobook
    0.47
    POSITIVE LOGITS
     Writing
    1.18
    Writing
    1.13
     writing
    1.11
    writing
    0.98
     writers
    0.94
     Writers
    0.94
    writers
    0.88
     scrittura
    0.83
     Schreib
    0.82
     escritura
    0.79
    Activations Density 0.128%

    No Known Activations