© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135885
    Prev
    Next
    INDEX
    Explanations

    following punctuation: "I", "people", "your", "existing", "just", "health"

    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_262k_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
    </h2>
    0.46
    itis
    0.44
    ately
    0.44
     ribs
    0.44
    ably
    0.44
    τευ
    0.43
    <0x0D>
    0.42
     zoo
    0.42
    貫
    0.41
    漬
    0.41
    POSITIVE LOGITS
     Kähler
    0.51
     હવા
    0.51
     İst
    0.50
     कैलाश
    0.50
     BSTC
    0.49
     bhfu
    0.49
     İyi
    0.48
    麝
    0.48
    ᴏ
    0.48
     człon
    0.48
    Activations Density 0.001%

    No Known Activations