© 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-262K
    7. 20965
    Prev
    Next
    INDEX
    Explanations

    market capitalization statistics

    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_262k_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
     smo
    0.43
    INGLE
    0.41
     overriding
    0.39
     温度
    0.39
    anmoins
    0.39
     CONSEQUENTIAL
    0.38
    yendo
    0.38
    ▷
    0.38
     smoot
    0.38
    meras
    0.38
    POSITIVE LOGITS
    рим
    0.40
     সঞ্জীবনী
    0.39
     Caen
    0.37
    醮
    0.36
     Zwe
    0.34
    োষ
    0.34
    sling
    0.34
    ائرة
    0.34
     marts
    0.34
    министра
    0.33
    Activations Density 0.002%

    No Known Activations