© 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. 30470
    Prev
    Next
    INDEX
    Explanations

    lists after punctuation

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

    medical, machine, temporal, higher, root

    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
    philos
    0.46
    ควร
    0.44
     ادبی
    0.44
     ہ
    0.44
    哲学
    0.44
    фф
    0.43
     politique
    0.43
    辜
    0.42
    转向
    0.42
     கழக
    0.42
    POSITIVE LOGITS
     enthalpies
    0.52
     unstimulated
    0.44
     carinatis
    0.43
     synapses
    0.42
     neurons
    0.42
     lobes
    0.42
     kabupaten
    0.42
     petals
    0.41
     spindles
    0.41
     initiates
    0.41
    Activations Density 0.002%

    No Known Activations