© 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. 34695
    Prev
    Next
    INDEX
    Explanations

    requires you or users

    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
     idade
    0.57
    larınız
    0.54
    📡
    0.53
    ياه
    0.53
     نفسك
    0.52
     wieku
    0.52
     empêcher
    0.51
     Vando
    0.48
     алыңыз
    0.48
    نيك
    0.48
    POSITIVE LOGITS
      
    0.54
     several
    0.53
     is
    0.51
    ,
    0.50
     l
    0.48
     selected
    0.47
     =
    0.46
     as
    0.46
     en
    0.45
    ang
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.