© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24535
    Prev
    Next
    INDEX
    Explanations

    dairy, tall, QK

    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
    anneau
    0.41
     REFERENCES
    0.41
    )}=
    0.39
    REFERENCES
    0.38
     kelle
    0.38
     heresy
    0.38
     requiere
    0.38
    )':
    0.38
     suficientemente
    0.38
     ಗೊತ್ತ
    0.38
    POSITIVE LOGITS
     চিন
    0.42
    Dairy
    0.40
    劇
    0.39
     ป
    0.38
    dairy
    0.38
    чина
    0.37
    Tall
    0.37
    quin
    0.37
    Film
    0.37
     Tall
    0.36
    Activations Density 0.000%

    No Known Activations