© 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. 62085
    Prev
    Next
    INDEX
    Explanations

    installation done

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

    quotes and services

    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
     Building
    0.49
     बिल्डिंग
    0.49
     సహాయ
    0.46
     تساعد
    0.46
    🏗
    0.45
     HVAC
    0.45
     Alkali
    0.44
     dealership
    0.44
     يساعد
    0.44
     Housing
    0.43
    POSITIVE LOGITS
     beğen
    0.43
     Wörter
    0.42
    Black
    0.42
     акку
    0.41
    black
    0.41
    écou
    0.40
    portrait
    0.40
    cov
    0.40
    骚
    0.40
    コスメ
    0.39
    Activations Density 0.086%

    No Known Activations