© 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. 70540
    Prev
    Next
    INDEX
    Explanations

    click on, UE technique, booking of

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

    automate, automation, scale

    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
     ಹೊಂದಿ
    0.46
    ipes
    0.43
    しまう
    0.43
    菓
    0.42
    ifer
    0.42
    ிரிய
    0.41
    あっ
    0.41
    申し上げ
    0.41
    問い
    0.41
     れ
    0.40
    POSITIVE LOGITS
    ב
    0.55
     מער
    0.55
    ('#
    0.53
     propel
    0.52
     Moab
    0.51
     automate
    0.50
     מו
    0.50
     powertrain
    0.49
     scuba
    0.49
    ك
    0.48
    Activations Density 0.000%

    No Known Activations