© 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. 45008
    Prev
    Next
    INDEX
    Explanations

    issues, mobile, mediated, dishes, religious

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

    potential returns or risk

    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
     permettra
    0.49
     économ
    0.49
    ཝ
    0.49
     francs
    0.48
     clés
    0.46
     renverse
    0.46
     divergents
    0.46
     éve
    0.46
     ৪০০
    0.46
    н
    0.46
    POSITIVE LOGITS
    bl
    0.59
    ar
    0.58
    1
    0.55
    eras
    0.54
    bg
    0.53
    fus
    0.51
    air
    0.51
    ul
    0.50
    ars
    0.50
    ole
    0.50
    Activations Density 0.000%

    No Known Activations