© 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. 142256
    Prev
    Next
    INDEX
    Explanations

    brand names or titles

    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
    ي
    0.69
    י
    0.63
    のが
    0.55
    i
    0.51
     doctrina
    0.50
     Ci
    0.49
    ch
    0.48
    de
    0.48
    м
    0.48
     воро
    0.48
    POSITIVE LOGITS
    ónio
    0.55
     xx
    0.52
    ็ด
    0.45
    ąda
    0.45
    EndTime
    0.45
    浿
    0.45
    iedad
    0.44
    พาะ
    0.44
    rosso
    0.44
    onucle
    0.44
    Activations Density 0.000%

    No Known Activations