© 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. 221306
    Prev
    Next
    INDEX
    Explanations

    protecting against misuse

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

    older phones, late March, delivery day

    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
     conced
    0.41
     staunch
    0.40
    ми
    0.40
    Références
    0.39
     affirme
    0.39
    зво
    0.38
    つつ
    0.38
     zarówno
    0.38
     obstante
    0.38
    ½
    0.38
    POSITIVE LOGITS
    ᅭ
    0.46
    膻
    0.45
     genius
    0.43
    可以是
    0.42
    FORD
    0.41
    POD
    0.40
     রূপ
    0.40
     முதல்வர்
    0.40
    耋
    0.40
     FORD
    0.40
    Activations Density 0.000%

    No Known Activations