© 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. 211300
    Prev
    Next
    INDEX
    Explanations

    after this point

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

    Company location

    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
     molécules
    0.50
    郄
    0.49
     вследствие
    0.48
    卜
    0.47
     desviación
    0.47
    또
    0.46
     relacionadas
    0.45
     músculos
    0.45
    骶
    0.45
     gráfica
    0.45
    POSITIVE LOGITS
    res
    0.55
     Uber
    0.54
     in
    0.54
     Circus
    0.53
    ille
    0.52
     Company
    0.52
    =
    0.51
     D
    0.50
    iller
    0.50
    in
    0.50
    Activations Density 0.000%

    No Known Activations