© 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. 210168
    Prev
    Next
    INDEX
    Explanations

    email address, establish, harmed or

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

    explaining why or how

    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
    ड्डा
    0.48
    𝘇
    0.47
    ماش
    0.46
    吸収
    0.45
     Regions
    0.44
     Podium
    0.42
    フォー
    0.42
    dioxide
    0.42
    徵
    0.42
    ิค
    0.41
    POSITIVE LOGITS
     durant
    0.52
     Folge
    0.49
     nunca
    0.48
     scena
    0.48
     meski
    0.48
    ✧
    0.48
    führer
    0.48
     erwarten
    0.45
     follow
    0.45
     proš
    0.45
    Activations Density 0.000%

    No Known Activations