© 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. 149970
    Prev
    Next
    INDEX
    Explanations

    Moon, shadow, numbers, sound

    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
     corrupción
    0.86
    sí
    0.84
    ಲ್ಯ
    0.84
    엣
    0.84
    髦
    0.84
     بمعنى
    0.84
     perdón
    0.83
    etz
    0.83
     osób
    0.80
    蜃
    0.80
    POSITIVE LOGITS
     Digital
    0.79
     डिजिटल
    0.77
     hea
    0.75
    आयु
    0.75
     digital
    0.74
    hões
    0.73
     energético
    0.73
    finite
    0.71
    ା
    0.71
     renew
    0.70
    Activations Density 0.001%

    No Known Activations