© 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. 189326
    Prev
    Next
    INDEX
    Explanations

    yearly starter greatest Christmas

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

    full of things

    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
     dysfunction
    0.51
     stimulates
    0.47
    §
    0.46
     manipul
    0.45
     cartil
    0.44
     stimuli
    0.44
     malfunctions
    0.44
    ุ
    0.43
     lesions
    0.42
     sexy
    0.42
    POSITIVE LOGITS
     Phạm
    0.59
     Teilnehmer
    0.55
     Lomb
    0.52
     있지만
    0.52
     Mitarbeit
    0.51
     Nouvelle
    0.50
     Бан
    0.50
     Realm
    0.50
     представитель
    0.49
     писатель
    0.48
    Activations Density 0.004%

    No Known Activations