© 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. 178436
    Prev
    Next
    INDEX
    Explanations

    gift basket, purest extracts, feast day

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

    native English speaker

    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
     क्योंकि
    0.50
     মতি
    0.50
     стрелец
    0.50
    ខ្ញ
    0.47
    埆
    0.46
     घरवालों
    0.45
    Гц
    0.45
    笥
    0.44
    詓
    0.44
    <unused2150>
    0.44
    POSITIVE LOGITS
     fossil
    0.49
     years
    0.48
    renewable
    0.43
     provenance
    0.43
     pork
    0.43
    anski
    0.42
     answers
    0.42
     overseas
    0.42
     study
    0.41
     presence
    0.41
    Activations Density 0.002%

    No Known Activations