© 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. 152092
    Prev
    Next
    INDEX
    Explanations

    pull out

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

    choir or model

    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
     Ericsson
    0.52
     Paralympic
    0.51
    aya
    0.50
    s
    0.50
    ن
    0.50
    ahu
    0.49
    is
    0.49
    uc
    0.48
    yan
    0.48
     Sunni
    0.48
    POSITIVE LOGITS
    ላል
    0.48
     knelt
    0.44
     hoping
    0.44
    ᥣ
    0.44
    願い
    0.43
     dorp
    0.43
     cane
    0.42
     hastily
    0.41
     wicker
    0.40
    ድን
    0.39
    Activations Density 0.002%

    No Known Activations