© 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. 111087
    Prev
    Next
    INDEX
    Explanations

    wheat powder

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

    fill half your plate

    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
    Not in Any Lists

    No Comments

    Negative Logits
     א
    0.52
     referencias
    0.49
     casamento
    0.48
     inverso
    0.46
     anteriores
    0.46
     llave
    0.46
     direitos
    0.46
    anzia
    0.45
    ١
    0.45
     comerciais
    0.45
    POSITIVE LOGITS
     diligently
    0.47
     duly
    0.45
    žete
    0.43
     wooded
    0.42
     vegetation
    0.41
     veggies
    0.39
     hearth
    0.39
     meticulously
    0.39
     speckled
    0.39
     coolest
    0.38
    Activations Density 0.000%

    No Known Activations