© 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. 24309
    Prev
    Next
    INDEX
    Explanations

    purring and yawning

    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
     ذریع
    0.50
    คาเดมี
    0.46
    悖
    0.42
    Substitute
    0.42
    .),
    0.41
     conçu
    0.41
    arıyla
    0.40
    儼
    0.40
    Purg
    0.40
    噩
    0.40
    POSITIVE LOGITS
     &
    0.48
     varient
    0.46
     colours
    0.46
     languages
    0.46
     остались
    0.44
     Brazil
    0.44
     Ireland
    0.43
     flavours
    0.43
     vowels
    0.43
     starten
    0.43
    Activations Density 0.001%

    No Known Activations