© 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. 17113
    Prev
    Next
    INDEX
    Explanations

    clan names

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

    structured data, foreign text

    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
    chluss
    0.49
    oció
    0.49
    denom
    0.48
     prioritizing
    0.47
    渕
    0.46
    द्योगिक
    0.45
     exclusionary
    0.45
     neuroscience
    0.45
    🌭
    0.44
     contacter
    0.44
    POSITIVE LOGITS
     Zeitschr
    0.54
     Kamer
    0.52
     Kamera
    0.51
     Lieut
    0.49
     довольно
    0.48
     izquierda
    0.47
     trabalhos
    0.47
     trabajos
    0.47
    拍摄
    0.46
     kamer
    0.45
    Activations Density 0.022%

    No Known Activations