© 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. 31-GEMMASCOPE-2-RES-262K
    7. 92257
    Prev
    Next
    INDEX
    Explanations

    special characters and structure

    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_31_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
    0.53
    ীয়
    0.48
    Са
    0.47
    וק
    0.45
    κει
    0.44
    ופ
    0.44
    "
    0.44
    ἃ
    0.44
     đức
    0.43
    يب
    0.43
    POSITIVE LOGITS
     prevention
    0.52
     siting
    0.50
     yoga
    0.49
     vigilant
    0.49
     vigilance
    0.49
     cardiology
    0.49
     guarantor
    0.48
     reins
    0.48
     fork
    0.48
     guarant
    0.48
    Activations Density 0.001%

    No Known Activations