© 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. 31-GEMMASCOPE-2-RES-65K
    7. 53316
    Prev
    Next
    INDEX
    Explanations

    qualifications and consequences

    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_65k_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
    ون
    0.51
    ку
    0.49
    Lowercase
    0.48
    ان
    0.48
    ᒐ
    0.47
     monopolies
    0.47
    کم
    0.45
    تر
    0.45
    ೂ
    0.45
    ⴳ
    0.45
    POSITIVE LOGITS
    they
    0.54
     Although
    0.52
     Hence
    0.49
    their
    0.48
    hence
    0.47
     hence
    0.46
     although
    0.46
    rails
    0.46
     Therefore
    0.45
     aunque
    0.44
    Activations Density 0.012%

    No Known Activations