© 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. 211054
    Prev
    Next
    INDEX
    Explanations

    New Mexico

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

    likely standard

    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
     It
    0.53
    It
    0.47
    it
    0.41
     ^
    0.40
     it
    0.40
     charged
    0.39
     Opposite
    0.38
     In
    0.38
    hrte
    0.38
     misused
    0.38
    POSITIVE LOGITS
    刄
    0.52
     namani
    0.45
     राजांनी
    0.44
    
    0.44
    ('').
    0.44
    椪
    0.43
    ทาน
    0.43
     brownie
    0.42
    🙌
    0.42
    )").
    0.42
    Activations Density 0.001%

    No Known Activations