© 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. 127360
    Prev
    Next
    INDEX
    Explanations

    design industries, dental students, pay interest

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

    dominant, want, he, efficiency, realistic

    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
    мо
    0.48
    াইতে
    0.47
    ünün
    0.46
    那
    0.46
     passengers
    0.45
     pushbutton
    0.45
    inputFields
    0.45
    Ц
    0.44
    桕
    0.44
    స్
    0.43
    POSITIVE LOGITS
     correctes
    0.48
    etis
    0.48
     Krat
    0.44
    castellan
    0.44
    leistungen
    0.44
    idemargin
    0.43
     euh
    0.43
     हित
    0.42
     निरा
    0.42
    ormap
    0.42
    Activations Density 0.000%

    No Known Activations