© 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. 190414
    Prev
    Next
    INDEX
    Explanations

    sector and all

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

    technical special characters and non-English

    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
    lia
    0.53
     liaison
    0.48
    )
    0.48
    oe
    0.46
     j
    0.45
     ı
    0.45
    JX
    0.45
    f
    0.45
    .)
    0.44
    PIA
    0.44
    POSITIVE LOGITS
    σε
    0.57
    சித்து
    0.55
    сите
    0.53
    ஸ்ரீ
    0.53
    ტომ
    0.52
    це
    0.51
    נ
    0.51
    сама
    0.50
     ಮೂಲ
    0.49
    ین
    0.48
    Activations Density 0.000%

    No Known Activations