© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13133
    Prev
    Next
    INDEX
    Explanations

    whether or not

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

    vs or vs

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

    say "o" words

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
    ).
    0.42
     $)$.
    0.42
    }.
    0.42
     ).
    0.41
     vendar
    0.41
    等
    0.41
     বলতে
    0.40
     }).
    0.39
    ęt
    0.38
    tidak
    0.38
    POSITIVE LOGITS
     oppure
    0.66
    หรือไม่
    0.57
     وبين
    0.47
    なのか
    0.46
     มั้ย
    0.45
    かは
    0.44
    還是
    0.43
     OR
    0.43
     maupun
    0.43
     tradicion
    0.43
    Activations Density 0.370%

    No Known Activations