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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212264
    Prev
    Next
    INDEX
    Explanations

    Orthodox type tell error vertist

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

    people prioritize imbalance learning

    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
     карта
    0.50
     زاويه
    0.49
    Colonne
    0.48
    녓
    0.44
    材质
    0.44
     വകു
    0.44
    目标的
    0.44
    里昂
    0.44
     കണ്ടെത്ത
    0.44
    诨
    0.44
    POSITIVE LOGITS
    fo
    0.59
     and
    0.58
    ido
    0.55
    sin
    0.54
    ers
    0.52
     eu
    0.52
    break
    0.50
    edu
    0.50
    eu
    0.50
    blo
    0.50
    Activations Density 0.001%

    No Known Activations