© 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-65K
    7. 47882
    Prev
    Next
    INDEX
    Explanations

    structured lists or code snippets

    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
    𝑔
    0.44
     occupe
    0.43
    p
    0.43
     esque
    0.42
     sicuramente
    0.42
    addEnemy
    0.42
    赝
    0.41
    𝗽
    0.41
    etern
    0.41
    cosa
    0.40
    POSITIVE LOGITS
    Codes
    0.43
    Ethics
    0.36
     ethics
    0.36
     desks
    0.35
     Oso
    0.35
    롤
    0.35
     booths
    0.34
     addresses
    0.33
     a
    0.33
    Scale
    0.33
    Activations Density 0.000%

    No Known Activations