© 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. 83866
    Prev
    Next
    INDEX
    Explanations

    ethical and responsible AI

    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
    r
    0.43
    6
    0.42
    successful
    0.41
    to
    0.41
    RS
    0.41
    rs
    0.40
    even
    0.39
    license
    0.39
    INGS
    0.38
    S
    0.38
    POSITIVE LOGITS
     elsewhere
    0.60
     dış
    0.53
     altri
    0.53
     بیشتر
    0.53
     Elsewhere
    0.52
     دیگر
    0.52
     nihil
    0.50
     інших
    0.48
     bolj
    0.48
     بجائے
    0.48
    Activations Density 0.023%

    No Known Activations