© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61859
    Prev
    Next
    INDEX
    Explanations

    Leonato, Flask, Resource

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.57
    -
    0.53
    z
    0.53
    g
    0.53
     for
    0.51
    サーバー
    0.51
    b
    0.51
    o
    0.50
    j
    0.49
    CD
    0.49
    POSITIVE LOGITS
     jugu
    0.55
     abhid
    0.54
     நன்கு
    0.53
     tractable
    0.52
    𒅆
    0.52
    ༣
    0.52
     silice
    0.51
     intractable
    0.50
     vitth
    0.50
     complejidad
    0.50
    Activations Density 0.002%

    No Known Activations