© 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. 128600
    Prev
    Next
    INDEX
    Explanations

    cooking, process improvement, historical eras, group affiliation

    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
    ()
    0.50
    >
    0.48
    ;;
    0.48
    ᱗
    0.45
    \%,
    0.44
    (-)
    0.44
    WW
    0.44
    naires
    0.43
    ITU
    0.43
    Unix
    0.42
    POSITIVE LOGITS
     kwenye
    0.57
     hingegen
    0.51
    णी
    0.47
     på
    0.46
     pada
    0.45
     showcased
    0.43
    𝖾
    0.42
    geordnet
    0.42
    ாஹ
    0.41
    })}$
    0.41
    Activations Density 0.005%

    No Known Activations