© 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. 49718
    Prev
    Next
    INDEX
    Explanations

    also great

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

    past results/common occurrences

    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
    -
    0.47
    time
    0.43
    nearly
    0.43
    gallery
    0.43
    ç
    0.43
    playing
    0.42
    an
    0.42
    ended
    0.41
    </i>
    0.41
    came
    0.41
    POSITIVE LOGITS
     prostit
    0.58
     auxqu
    0.58
     isAdmin
    0.55
    𝐪
    0.52
     julg
    0.52
     exemplaires
    0.51
     exclusives
    0.50
     ähm
    0.49
     achats
    0.49
    দানি
    0.49
    Activations Density 0.000%

    No Known Activations