© 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. 28395
    Prev
    Next
    INDEX
    Explanations

    foreign language or technical terms

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

    comparing different historical periods

    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
    栍
    0.60
     beträgt
    0.55
     Existem
    0.54
    躹
    0.53
     моби
    0.52
    棒
    0.51
     dwie
    0.50
     Apica
    0.50
    婍
    0.50
     ين
    0.50
    POSITIVE LOGITS
    로는
    0.46
     તાલુ
    0.43
    ιλ
    0.42
    posals
    0.39
    当社
    0.39
     सुनील
    0.39
    良く
    0.38
     contraceptives
    0.38
     surgeries
    0.38
    मै
    0.37
    Activations Density 0.000%

    No Known Activations