© 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. 196224
    Prev
    Next
    INDEX
    Explanations

    aspiring singer

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

    criminal penalties

    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
    ê
    0.55
    ’
    0.50
     inhabitants
    0.46
     respectivement
    0.45
     ഇക്കാര
    0.45
     affirme
    0.45
    پ
    0.45
     ഉ
    0.44
    โ
    0.44
    zar
    0.44
    POSITIVE LOGITS
     Melan
    0.56
    燔
    0.50
    ंखला
    0.49
     Falun
    0.48
     Cookie
    0.47
    品种
    0.46
     Monet
    0.46
     juda
    0.46
    צת
    0.46
     Thesis
    0.46
    Activations Density 0.001%

    No Known Activations