© 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. 74070
    Prev
    Next
    INDEX
    Explanations

    possible combinations, buddy, reserves, ready, deliver, pretentious

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

    need or want to

    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
     hypothyroidism
    0.47
    苹果
    0.46
    لية
    0.46
    بيرة
    0.46
    iziModal
    0.46
     affidavit
    0.46
    alumno
    0.45
    ノ
    0.45
     aurora
    0.45
    لی
    0.43
    POSITIVE LOGITS
     PPR
    0.57
    occupied
    0.46
     सफाई
    0.45
     Five
    0.44
    న్నీ
    0.44
     compt
    0.44
    ówn
    0.44
    meets
    0.43
    ównie
    0.43
     FRP
    0.42
    Activations Density 0.001%

    No Known Activations