© 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. 244361
    Prev
    Next
    INDEX
    Explanations

    angles, π/2, π/3, 3π/5

    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
    𝑉
    0.47
    psr
    0.44
     endow
    0.44
    뛴
    0.43
    TreeNavigator
    0.43
    েন্স
    0.42
    ksh
    0.42
     inflate
    0.42
    )$
    0.41
     solidify
    0.41
    POSITIVE LOGITS
     vous
    0.53
    äten
    0.49
    á
    0.48
    å
    0.48
    athon
    0.47
    igans
    0.47
    até
    0.47
    Ᏺ
    0.46
    idge
    0.46
     ayant
    0.46
    Activations Density 0.000%

    No Known Activations