© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 194301
    Prev
    Next
    INDEX
    Explanations

    online news, magazines

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

    emojis and AI terms

    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
    zaam
    0.49
    plasia
    0.47
     كمان
    0.45
    `;
    0.44
     ;-)
    0.44
    züge
    0.43
     comando
    0.43
     যেন
    0.43
    zków
    0.43
    '=>$
    0.43
    POSITIVE LOGITS
    θο
    0.52
    มั่น
    0.52
     visibles
    0.51
     agres
    0.49
    ਾਨੂੰ
    0.49
     écl
    0.47
    ทธิ
    0.47
    ASCII
    0.46
    ORS
    0.46
    ARY
    0.45
    Activations Density 0.000%

    No Known Activations