© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149870
    Prev
    Next
    INDEX
    Explanations

    be plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hier
    0.73
     "
    0.68
    シリ
    0.67
    dotenv
    0.65
    そらく
    0.64
     chyba
    0.63
    はじ
    0.63
    queous
    0.63
    hier
    0.62
    Given
    0.62
    POSITIVE LOGITS
     applications
    0.87
    应用的
    0.82
     voicemail
    0.82
     Applications
    0.82
    ଠ
    0.82
    应用
    0.81
    應用
    0.81
     appli
    0.80
     firmware
    0.79
    ◌
    0.79
    Activations Density 0.002%

    No Known Activations