© 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. 139079
    Prev
    Next
    INDEX
    Explanations

    Ed, Isaac, Oren, Reuben, industry

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

    writing or specific subjects

    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
     đây
    0.52
     динами
    0.52
     இவ்வ
    0.51
    钅
    0.51
     ибо
    0.51
     atque
    0.50
     fêtes
    0.50
    <start_of_turn>
    0.49
     இங்கு
    0.49
    了这个
    0.49
    POSITIVE LOGITS
     Ed
    0.47
     I
    0.45
    小心
    0.43
     Isaac
    0.43
     industry
    0.43
     direction
    0.43
     Oren
    0.42
     Rev
    0.42
     Reuben
    0.42
     Fores
    0.42
    Activations Density 0.001%

    No Known Activations