© 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. 89581
    Prev
    Next
    INDEX
    Explanations

    Lord has, introduced into, common symptoms, Marvel

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

    copy and paste

    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
    MON
    0.45
    量的
    0.44
    า
    0.44
    檚
    0.42
    ポーター
    0.42
    נ
    0.42
    ರಿಸ
    0.41
    ζ
    0.41
     मैनेज
    0.41
     ল
    0.40
    POSITIVE LOGITS
     sofa
    0.54
     biru
    0.53
     negeri
    0.52
     klas
    0.49
     Sofa
    0.49
     sama
    0.49
     fairies
    0.49
     teman
    0.48
     tuf
    0.48
     konkre
    0.47
    Activations Density 0.000%

    No Known Activations