© 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. 242943
    Prev
    Next
    INDEX
    Explanations

    commands and configurations

    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
     bmw
    0.52
     paisajes
    0.50
     behav
    0.48
     و
    0.47
     gps
    0.47
     αλλά
    0.47
     webs
    0.46
     BMW
    0.46
     happenings
    0.46
     landscapes
    0.46
    POSITIVE LOGITS
    ൪
    0.47
    ת
    0.45
    owanych
    0.45
    туру
    0.43
    釷
    0.43
    ೧
    0.43
    ᒐ
    0.43
    檴
    0.42
    朮
    0.42
    Machine
    0.41
    Activations Density 0.001%

    No Known Activations