© 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. 124519
    Prev
    Next
    INDEX
    Explanations

    near location, Robot De, quartz stone, unless otherwise

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

    CBT therapy

    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
     studia
    0.45
     تمر
    0.44
     Ruf
    0.44
     структур
    0.42
     chỉnh
    0.42
     глав
    0.41
     D
    0.40
     Го
    0.40
     تعلم
    0.39
     Học
    0.38
    POSITIVE LOGITS
    luck
    0.49
     microbiota
    0.48
    hypothesis
    0.48
    uc
    0.48
    ld
    0.46
    ocyst
    0.46
    abhavena
    0.46
    ande
    0.46
    pland
    0.45
     disant
    0.45
    Activations Density 0.001%

    No Known Activations