© 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. 149942
    Prev
    Next
    INDEX
    Explanations

    let's face it

    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
    ⋮
    0.77
     truth
    0.72
    truth
    0.70
     potwier
    0.68
     version
    0.68
    원본
    0.67
     confir
    0.66
    .+
    0.65
     بتا
    0.64
    FEATURE
    0.64
    POSITIVE LOGITS
    istics
    0.84
     arctic
    0.78
    ackle
    0.77
     bakteri
    0.77
    asjoner
    0.77
     Arctic
    0.76
    σουμε
    0.75
    íticas
    0.75
     ماحول
    0.75
    atron
    0.75
    Activations Density 0.001%

    No Known Activations