© 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. 6368
    Prev
    Next
    INDEX
    Explanations

    places, roles, and concepts

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

    relationships, work, or tasks

    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
    ៕
    0.40
     XNUMX
    0.40
    0.38
     VERY
    0.38
    )}
    0.38
     appunto
    0.37
     very
    0.37
     შესახებ
    0.37
     ಸ್ವಲ್ಪ
    0.35
    ֖
    0.35
    POSITIVE LOGITS
     কিংবা
    0.80
     mesela
    0.79
    したり
    0.74
     ebenso
    0.69
    はもちろん
    0.68
     যেমন
    0.64
     oppure
    0.61
     bijvoorbeeld
    0.61
     misalnya
    0.59
    いたり
    0.58
    Activations Density 0.413%

    No Known Activations