© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13388
    Prev
    Next
    INDEX
    Explanations

    track record

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    赶
    0.52
     féidir
    0.50
     invalid
    0.49
     зави
    0.48
    无穷
    0.48
     }()
    0.48
    ństwa
    0.47
     infin
    0.47
     সর্বনাশ
    0.47
    ހ
    0.47
    POSITIVE LOGITS
     track
    3.00
    track
    2.69
     Track
    2.58
    Track
    2.50
     ट्रैक
    2.28
     record
    2.20
     TRACK
    2.19
    record
    2.13
     history
    2.09
    TRACK
    2.02
    Activations Density 0.108%

    No Known Activations