© 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. 16-GEMMASCOPE-2-RES-65K
    7. 397
    Prev
    Next
    INDEX
    Explanations

    introducing findings or contrasts

    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_16_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
    د
    0.37
    دت
    0.36
    دد
    0.35
     accesorios
    0.33
    دين
    0.33
    دون
    0.32
    лятор
    0.32
     עבור
    0.30
     Interestingly
    0.30
     удар
    0.30
    POSITIVE LOGITS
    of
    0.46
    the
    0.45
    and
    0.35
    пе
    0.35
    き
    0.34
    রা
    0.32
     be
    0.32
    یس
    0.32
     the
    0.31
     are
    0.31
    Activations Density 0.394%

    No Known Activations