© 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. 104476
    Prev
    Next
    INDEX
    Explanations

    French, vintage, time, warranty

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

    liminal spaces, nostalgia, early internet

    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
     company
    0.46
    T
    0.46
     hia
    0.44
     ,
    0.42
     him
    0.42
    Youtube
    0.42
      
    0.41
    真人
    0.41
     his
    0.40
    Java
    0.40
    POSITIVE LOGITS
     mécanisme
    0.57
    motionProxy
    0.56
    KSprite
    0.55
     പിന്നീ
    0.53
     vorbere
    0.51
     следующие
    0.50
    <unused89>
    0.49
     Ман
    0.49
     mecanismos
    0.48
     neuropsych
    0.48
    Activations Density 0.001%

    No Known Activations