© 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. 147496
    Prev
    Next
    INDEX
    Explanations

    signup button

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

    best first

    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
    ajte
    0.54
     কাক
    0.53
     गोबर
    0.52
     कमाई
    0.50
     योग्यता
    0.50
    ithvi
    0.49
     क्लब
    0.48
    मॉन
    0.48
     नारियल
    0.48
    <unused51>
    0.46
    POSITIVE LOGITS
    ен
    0.52
    ра
    0.49
     näher
    0.47
     shift
    0.46
     el
    0.44
     ion
    0.44
     suspicion
    0.43
    ר
    0.43
    й
    0.42
     n
    0.42
    Activations Density 0.000%

    No Known Activations