© 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. 57460
    Prev
    Next
    INDEX
    Explanations

    open at

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

    evolution of dogs, construction, development

    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
    ✫
    0.46
    愆
    0.46
    ("^
    0.45
    ($_
    0.43
     эмоциона
    0.43
     قائمة
    0.42
    ∈
    0.41
     bodhis
    0.41
    ℏ
    0.41
     ছুই
    0.41
    POSITIVE LOGITS
    כנס
    0.45
     Villas
    0.44
     ຊ
    0.44
    SSON
    0.43
    dX
    0.42
     عرصے
    0.42
     Wa
    0.42
     prea
    0.42
     Tammy
    0.41
     Avner
    0.41
    Activations Density 0.000%

    No Known Activations