© 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. 7286
    Prev
    Next
    INDEX
    Explanations

    base currency, standard port, his address

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

    this is why

    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
     i
    0.64
    4
    0.61
     Help
    0.59
     Best
    0.59
    ij
    0.57
     Fit
    0.56
    Best
    0.56
     h
    0.55
    ist
    0.55
     t
    0.54
    POSITIVE LOGITS
    鯱
    0.60
     rupani
    0.54
    indexBuffer
    0.53
    㖣
    0.52
     RENDITION
    0.51
    ەیە
    0.49
    惪
    0.49
    まし
    0.48
    ORICAL
    0.48
    ويلة
    0.48
    Activations Density 0.000%

    No Known Activations