© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138909
    Prev
    Next
    INDEX
    Explanations

    progress bar library `tqdm`

    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
    𝘬
    0.68
     လ
    0.63
    𝑘
    0.63
    <0xF2>
    0.62
     także
    0.61
    مس
    0.60
     famí
    0.59
    ش
    0.59
     Eksp
    0.57
     Biraz
    0.57
    POSITIVE LOGITS
     concrete
    0.60
     countertops
    0.56
     profusely
    0.56
     (
    0.55
     salaried
    0.54
     penthouse
    0.53
    ειας
    0.53
    sey
    0.50
     breakthrough
    0.50
     businessman
    0.49
    Activations Density 0.001%

    No Known Activations