© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139767
    Prev
    Next
    INDEX
    Explanations

    possible email formats

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

    command control settings

    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
    }^{*}$,
    0.54
    ूटूथ
    0.52
     métall
    0.50
    habit
    0.49
     offrent
    0.48
     Jé
    0.48
     accès
    0.47
    tellers
    0.47
    govern
    0.46
    }^{*}$
    0.46
    POSITIVE LOGITS
    Builder
    0.43
    ToServer
    0.43
     watermelon
    0.42
     Bounce
    0.41
    Module
    0.40
    來
    0.40
     รี
    0.39
    新規
    0.38
     cliche
    0.38
     Crossroads
    0.38
    Activations Density 0.001%

    No Known Activations