© 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. 189958
    Prev
    Next
    INDEX
    Explanations

    able to

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

    secondary emotion, phenomenon, root cause, foundations

    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
     incons
    0.41
     physically
    0.40
    лись
    0.40
     escaped
    0.39
     süre
    0.39
     книг
    0.39
    poli
    0.39
    纷
    0.39
     ORIG
    0.38
     Unesco
    0.38
    POSITIVE LOGITS
     তাছাড়া
    0.50
    籁
    0.50
    Saw
    0.46
    Ꮐ
    0.44
    ०
    0.43
     टेबलेट
    0.41
    Mike
    0.41
     dimana
    0.40
    Matt
    0.40
    不然
    0.40
    Activations Density 0.000%

    No Known Activations