© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 143374
    Prev
    Next
    INDEX
    Explanations

    okay, okay, followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    র্ত
    0.72
    ্ব
    0.57
    ა
    0.57
    א
    0.57
    надцать
    0.56
     Johann
    0.55
    다
    0.55
    ל
    0.53
    য়
    0.53
    ද්ග
    0.52
    POSITIVE LOGITS
     meadows
    0.68
    t
    0.63
     to
    0.62
    SNR
    0.61
    _
    0.61
    क्लेव
    0.60
     grasslands
    0.59
     smuggling
    0.57
     uninhab
    0.57
    tive
    0.57
    Activations Density 0.007%

    No Known Activations