© 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. 40-GEMMASCOPE-2-RES-262K
    7. 33743
    Prev
    Next
    INDEX
    Explanations

    recent linkage

    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_40_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
     наша
    0.42
     our
    0.39
     нашу
    0.38
     нашем
    0.38
    our
    0.38
    棘
    0.37
    Estimation
    0.37
    ಪಾ
    0.37
     который
    0.37
     наш
    0.37
    POSITIVE LOGITS
    freq
    0.38
     frequency
    0.38
     periodicals
    0.35
    successor
    0.35
    Linked
    0.34
     lm
    0.34
     oman
    0.34
    क्रिप्शन
    0.33
     freq
    0.33
    燎
    0.33
    Activations Density 0.009%

    No Known Activations