© 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. 198519
    Prev
    Next
    INDEX
    Explanations

    insurance advice

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

    estimates and disclaimers

    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
    勮
    0.56
    esempio
    0.54
    και
    0.52
    Ꮸ
    0.52
    čke
    0.50
    ceaux
    0.50
    ビーチ
    0.50
    音楽
    0.49
    accompagn
    0.49
    蜉
    0.48
    POSITIVE LOGITS
    0.45
     Soll
    0.44
    Needs
    0.41
     Flu
    0.41
     Konto
    0.40
     expense
    0.39
     alma
    0.38
     Needs
    0.38
     Hazard
    0.38
     Ledger
    0.38
    Activations Density 0.001%

    No Known Activations