© 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. 138183
    Prev
    Next
    INDEX
    Explanations

    names and quantities

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

    words ending in ify or ology

    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
    ANCED
    0.45
    ENAME
    0.42
    🕴
    0.42
    Enqueue
    0.41
    UNDO
    0.40
    Replacement
    0.39
    Appointments
    0.39
    Metall
    0.38
    сси
    0.38
    opez
    0.38
    POSITIVE LOGITS
    marketing
    0.47
     icin
    0.46
    images
    0.46
     говори
    0.46
     dla
    0.45
     multiplicar
    0.45
    bell
    0.45
     !
    0.44
    am
    0.44
     cantar
    0.44
    Activations Density 0.001%

    No Known Activations