© 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. 249441
    Prev
    Next
    INDEX
    Explanations

    Blackjack

    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
    avut
    0.45
    反
    0.44
     expuls
    0.43
    তরাং
    0.42
     marquées
    0.42
    र्ज
    0.42
    ग्विजय
    0.41
     distanceFrom
    0.41
     Targeting
    0.40
    ？）
    0.40
    POSITIVE LOGITS
    Ś
    0.45
    retro
    0.43
    ͑
    0.43
    Č
    0.43
    ล์
    0.42
    ۡ
    0.42
     معظم
    0.42
     сві
    0.41
     تاثیر
    0.41
    Ć
    0.41
    Activations Density 0.000%

    No Known Activations