© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191190
    Prev
    Next
    INDEX
    Explanations

    DNA evidence

    np_acts-logits-general · gemini-2.5-flash-lite

    analyzing questions about feelings or predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    colFirst
    0.48
    pies
    0.47
    ecie
    0.47
    披露
    0.47
    reh
    0.47
    journal
    0.46
    ↵↵
    0.46
    チョ
    0.46
    Regulatory
    0.45
    Culture
    0.45
    POSITIVE LOGITS
     sonuc
    0.51
     FRIEND
    0.47
    徬
    0.42
     tempo
    0.42
    ెంబ
    0.41
     dobro
    0.41
     looser
    0.41
     socket
    0.41
     যাহার
    0.41
     syk
    0.40
    Activations Density 0.000%

    No Known Activations