© 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. 37734
    Prev
    Next
    INDEX
    Explanations

    outer edge

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

    programming languages, songs, cities, academic degrees

    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
    ান
    0.48
    Fuel
    0.47
    কৃ
    0.47
    MX
    0.46
    ate
    0.45
     டன்
    0.45
    provides
    0.45
    л
    0.45
    nero
    0.44
    MLB
    0.44
    POSITIVE LOGITS
     injustices
    0.50
     jantar
    0.46
     pertumbuhan
    0.45
     walaupun
    0.45
     satire
    0.44
     exposé
    0.43
     debunk
    0.43
     pseud
    0.42
     fals
    0.42
     antisemit
    0.42
    Activations Density 0.000%

    No Known Activations