© 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. 242148
    Prev
    Next
    INDEX
    Explanations

    specific nouns and phrases

    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
    取り組み
    0.52
     hashing
    0.48
    ズム
    0.47
     obituary
    0.47
    駅
    0.45
    izedBox
    0.44
    係
    0.44
     UNNEEDED
    0.44
     (/
    0.44
     homeomorphism
    0.44
    POSITIVE LOGITS
    ir
    0.57
    pples
    0.50
    irane
    0.48
    ICLES
    0.47
     igualmente
    0.46
    irar
    0.45
     å
    0.44
     adultos
    0.44
     একই
    0.44
     clientes
    0.43
    Activations Density 0.001%

    No Known Activations