© 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. 95094
    Prev
    Next
    INDEX
    Explanations

    counting periods and quantities

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

    greeting and explanation

    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
    Если
    0.45
     acost
    0.44
    이제
    0.42
     amico
    0.40
    裹
    0.40
     selain
    0.39
    дак
    0.39
     когато
    0.39
     prilikom
    0.39
    ծ
    0.39
    POSITIVE LOGITS
     applause
    0.46
     République
    0.45
     Eight
    0.45
     intelligent
    0.43
     influential
    0.43
    ecological
    0.43
    developed
    0.43
     uproar
    0.42
     คณิตศาสตร์
    0.41
     ILO
    0.40
    Activations Density 0.001%

    No Known Activations