© 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-262K
    7. 99897
    Prev
    Next
    INDEX
    Explanations

    utility improvements

    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
    ̱
    0.45
    ul
    0.44
    ’),
    0.44
    ivals
    0.41
     width
    0.41
     washing
    0.41
    ajjati
    0.41
    分けて
    0.41
     provocative
    0.40
     watery
    0.40
    POSITIVE LOGITS
     rumores
    0.49
    -
    0.46
    Sobre
    0.46
     Desenvolvimento
    0.45
     exped
    0.45
    عبة
    0.45
     expedite
    0.44
     López
    0.44
    !
    0.43
    Beat
    0.43
    Activations Density 0.003%

    No Known Activations