© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 8386
    Prev
    Next
    INDEX
    Explanations

    distribute copies and modified versions

    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
     تع
    0.27
     اللا
    0.26
    諦
    0.26
     úd
    0.25
     bors
    0.25
     règ
    0.25
     toi
    0.25
     doh
    0.25
    Excuse
    0.25
     specifiche
    0.24
    POSITIVE LOGITS
    ²
    0.25
    뤽
    0.25
    _
    0.24
     Impacts
    0.23
     Learning
    0.23
     प्रोडक्शन
    0.23
    -
    0.22
    the
    0.22
     Developments
    0.22
     developments
    0.22
    Activations Density 0.001%

    No Known Activations