© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80202
    Prev
    Next
    INDEX
    Explanations

    dialogue cues

    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
    Negative Logits
     alleviating
    0.48
     misdemeanor
    0.46
     abrasive
    0.46
    <unused2179>
    0.46
     adversarial
    0.45
     sulfide
    0.45
     unsubstituted
    0.45
    <unused2173>
    0.45
     explosives
    0.43
     injurious
    0.42
    POSITIVE LOGITS
    Ahora
    0.47
    Elementos
    0.45
    Mo
    0.44
    蔬
    0.44
    Saund
    0.43
    Bes
    0.43
    ㅉ
    0.43
    Faucet
    0.42
    Viewing
    0.42
    Flower
    0.41
    Activations Density 0.007%

    No Known Activations