© 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. 146784
    Prev
    Next
    INDEX
    Explanations

    annual visits or inspections

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

    brainstorminglistingsuggestionspotentialideas

    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
     elb
    0.54
     appena
    0.53
    robat
    0.48
     három
    0.48
     cí
    0.48
     sieben
    0.48
     wiel
    0.47
     drei
    0.43
     bimod
    0.43
     γ
    0.43
    POSITIVE LOGITS
     WHY
    0.44
    ]])
    0.44
    ENTAL
    0.42
    衛生
    0.42
    Why
    0.40
    Detal
    0.40
    Flicky
    0.39
    Pile
    0.39
    kog
    0.39
    MgO
    0.38
    Activations Density 0.001%

    No Known Activations