© 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. 238623
    Prev
    Next
    INDEX
    Explanations

    article abstracts and topics

    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
     نہ
    0.54
     а
    0.52
     Maschine
    0.50
     coin
    0.49
     Joaquín
    0.49
     conciencia
    0.49
     unoccupied
    0.48
     cassette
    0.48
     생
    0.47
     syphilis
    0.46
    POSITIVE LOGITS
    t
    0.53
    limsup
    0.48
    drops
    0.48
    start
    0.46
    و
    0.46
    dW
    0.45
    ERR
    0.44
    mom
    0.44
    在一
    0.43
    cena
    0.43
    Activations Density 0.000%

    No Known Activations