© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154666
    Prev
    Next
    INDEX
    Explanations

    is one of

    np_acts-logits-general · gemini-2.5-flash-lite

    understanding concepts and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鱈
    0.49
    nytimes
    0.48
    瘧
    0.47
    鎳
    0.46
    tra
    0.45
    tid
    0.45
    amati
    0.45
    倪
    0.45
    told
    0.44
    പ്പെടുന്ന
    0.43
    POSITIVE LOGITS
     contralateral
    0.53
     rains
    0.52
     hookah
    0.50
     by
    0.48
     unbreakable
    0.48
     quietly
    0.48
     अखंड
    0.47
     sultry
    0.47
     with
    0.47
     owns
    0.46
    Activations Density 0.001%

    No Known Activations