© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91943
    Prev
    Next
    INDEX
    Explanations

    brain-created reality maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cravings
    0.44
     nonostante
    0.42
     நான்
    0.42
    我不
    0.42
     industrie
    0.42
     mujhe
    0.41
     我
    0.40
     ผม
    0.40
     instinct
    0.40
     souhaitez
    0.40
    POSITIVE LOGITS
     বিবরণ
    0.48
     inaccurate
    0.43
     COLLATION
    0.43
     hh
    0.43
     LOCAL
    0.42
    这个
    0.41
     separately
    0.40
     at
    0.40
     герои
    0.40
     those
    0.40
    Activations Density 0.007%

    No Known Activations