© 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. 7959
    Prev
    Next
    INDEX
    Explanations

    avoidselective foreign terms

    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
    :
    0.59
     de
    0.58
     remembers
    0.50
     Adams
    0.48
     Structures
    0.48
     menc
    0.48
     (`
    0.48
     Beers
    0.47
     Things
    0.47
     Green
    0.46
    POSITIVE LOGITS
    ⟣
    0.56
     ferrugineux
    0.51
    ബന്ധ
    0.51
    ലീസ്
    0.49
     rufo
    0.49
    𝔯
    0.49
     pédicule
    0.49
    会社
    0.48
     ritorno
    0.47
     conflitto
    0.47
    Activations Density 0.000%

    No Known Activations