© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22798
    Prev
    Next
    INDEX
    Explanations

    ye followed by oman or at or yeasty

    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_40_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
    ಿತಿ
    0.46
    گاه
    0.43
     Trời
    0.42
    lès
    0.41
    scriptstyle
    0.40
     তুর
    0.38
    ቾ
    0.38
    änder
    0.38
     Discussions
    0.38
    diamine
    0.38
    POSITIVE LOGITS
    穌
    0.53
    Ye
    0.50
     ye
    0.45
    şil
    0.44
    omans
    0.42
    Granted
    0.42
     platz
    0.39
     vieja
    0.39
    蓁
    0.39
    Separator
    0.38
    Activations Density 0.003%

    No Known Activations