© 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. 52354
    Prev
    Next
    INDEX
    Explanations

    severe, recently dumped, nose

    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
    🏽
    0.50
    🏾
    0.45
     qualcosa
    0.44
     adequately
    0.44
    Healthcare
    0.44
     envisioned
    0.43
     responsabil
    0.43
    Kathy
    0.42
     programas
    0.42
     ব্যবস
    0.41
    POSITIVE LOGITS
     निकट
    0.49
    dari
    0.46
     యుద్ధ
    0.45
    욕
    0.45
    ៧
    0.45
    сподар
    0.45
     속
    0.45
    nl
    0.44
    ลาย
    0.44
    utage
    0.43
    Activations Density 0.005%

    No Known Activations