© 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. 123005
    Prev
    Next
    INDEX
    Explanations

    definitions or teachings

    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
    ⵣ
    0.47
    𒄩
    0.46
    촬
    0.46
     plata
    0.45
    ज़ार
    0.45
    ępow
    0.44
    侸
    0.44
     schematically
    0.43
     πληροφο
    0.43
    恤
    0.43
    POSITIVE LOGITS
    0.54
     AB
    0.53
     BRA
    0.46
     maintained
    0.46
     {
    0.45
     WR
    0.45
     AL
    0.45
     ASS
    0.44
     Ba
    0.44
     ABS
    0.44
    Activations Density 0.006%

    No Known Activations