© 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. 153867
    Prev
    Next
    INDEX
    Explanations

    foundations of book titles

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

    politics, evolution, origins, handbook, transition

    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
    jacke
    0.54
     വിജയ
    0.50
    ationen
    0.50
    Ᏺ
    0.50
     شلون
    0.48
    怆
    0.48
     获取
    0.47
     बढ़कर
    0.47
     मर्दों
    0.47
    觎
    0.47
    POSITIVE LOGITS
     Feb
    0.44
     swivel
    0.43
     wyp
    0.41
     unify
    0.41
     Ped
    0.39
     nook
    0.39
    ILL
    0.39
     cont
    0.38
     memper
    0.38
     dis
    0.38
    Activations Density 0.001%

    No Known Activations