© 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. 191318
    Prev
    Next
    INDEX
    Explanations

    plastic items, mouthfeel, downloaded files, persons, expense, palette, straps

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

    mental health and wellbeing

    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
    였다
    0.49
    с
    0.48
    ズ
    0.46
    и
    0.45
    մ
    0.45
    рі
    0.45
    і
    0.45
    യായിരുന്നു
    0.44
    п
    0.43
    थी
    0.43
    POSITIVE LOGITS
     aspiring
    0.48
     benzoic
    0.44
     algal
    0.43
     arginine
    0.43
     inaugurated
    0.42
     Philippine
    0.42
     PubMed
    0.42
     nascent
    0.42
     yielded
    0.41
     cautiously
    0.41
    Activations Density 0.001%

    No Known Activations