© 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. 12110
    Prev
    Next
    INDEX
    Explanations

    buckle up

    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
    arcía
    0.59
     Hodges
    0.58
    ”
    0.57
    cretsiz
    0.55
     It
    0.54
    ک
    0.52
    ziger
    0.51
    newcommand
    0.50
    ául
    0.50
    nA
    0.50
    POSITIVE LOGITS
    Ꮋ
    0.52
     harsher
    0.51
    шена
    0.50
     zatem
    0.50
     THAT
    0.50
     （
    0.50
     toned
    0.50
     будь
    0.50
     pueden
    0.49
     bọn
    0.49
    Activations Density 0.033%

    No Known Activations