© 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. 142908
    Prev
    Next
    INDEX
    Explanations

    long time since

    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
     specif
    0.63
     sting
    0.58
     маник
    0.57
     repert
    0.57
    ੪
    0.57
     subsidized
    0.57
     docile
    0.56
     facial
    0.55
     pati
    0.54
     financially
    0.54
    POSITIVE LOGITS
    ighthouse
    0.66
    ص
    0.63
    lj
    0.62
    Sanchez
    0.59
    sk
    0.59
    tx
    0.58
    ל
    0.58
    Ed
    0.57
    Imagen
    0.56
     Agustín
    0.55
    Activations Density 0.001%

    No Known Activations