© 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. 211262
    Prev
    Next
    INDEX
    Explanations

    contraction contractions

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

    naming conventions and quantities

    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
    to
    0.59
    t
    0.57
    rather
    0.49
    ط
    0.49
    typically
    0.47
    то
    0.46
    يب
    0.46
     prácticamente
    0.46
    ۈ
    0.45
    ru
    0.45
    POSITIVE LOGITS
     renovate
    0.52
     пас
    0.46
     renovated
    0.45
     instances
    0.44
    헨
    0.43
     violence
    0.42
     pensioners
    0.42
     dorso
    0.42
     discover
    0.41
     debts
    0.41
    Activations Density 0.005%

    No Known Activations