© 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. 67590
    Prev
    Next
    INDEX
    Explanations

    daily access

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

    strengths and sodium

    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
    Jeśli
    0.64
     Якщо
    0.60
     όταν
    0.54
    dyž
    0.53
    Hvis
    0.53
    োলার
    0.53
    єте
    0.50
    雱
    0.50
    iedy
    0.49
    VideoButton
    0.49
    POSITIVE LOGITS
     Moreover
    0.61
     Furthermore
    0.58
     Economist
    0.54
     sekaligus
    0.52
     importantly
    0.51
     thirteen
    0.51
     ,
    0.50
     furthermore
    0.50
     moreover
    0.49
     interestingly
    0.49
    Activations Density 0.002%

    No Known Activations