© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9571
    Prev
    Next
    INDEX
    Explanations

    key, keys, and musical keys

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

    dictionary keys

    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_40_width_16k_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
     اظ
    0.40
     äl
    0.36
    ('/');
    0.34
    টারে
    0.34
    倫
    0.34
    ട്ടി
    0.34
    зне
    0.34
    তুন
    0.33
    掩
    0.33
    ገ
    0.33
    POSITIVE LOGITS
     key
    2.55
    key
    2.41
     клю
    2.17
     keys
    2.16
     KEY
    2.13
    Key
    2.11
     Key
    2.09
    KEY
    2.08
     ключ
    2.05
     ключе
    1.97
    Activations Density 0.117%

    No Known Activations