© 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. 101827
    Prev
    Next
    INDEX
    Explanations

    seeing or finding differences

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

    specific

    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
    НІ
    0.48
    هره
    0.42
     trouva
    0.42
    ماً
    0.41
    Ꮷ
    0.41
    ТС
    0.41
    ươ
    0.39
     அமெ
    0.39
     atleast
    0.39
    ܤ
    0.39
    POSITIVE LOGITS
     ဆ
    0.50
     caching
    0.48
     geometrical
    0.47
     mathematical
    0.46
     vibrational
    0.45
    鹈
    0.45
     polys
    0.43
     xWidth
    0.43
    velocityY
    0.42
     sacram
    0.42
    Activations Density 0.002%

    No Known Activations