© 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. 53729
    Prev
    Next
    INDEX
    Explanations

    Shared or liability insurance

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

    signifies metastasis, still echoing, philosophical approaches, statues

    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
     evidentemente
    0.54
     shipbuilding
    0.53
     aussitôt
    0.51
    ింది
    0.50
     ontstaan
    0.49
     periódico
    0.49
    鷸
    0.49
     thorns
    0.48
     прида
    0.48
     tipo
    0.48
    POSITIVE LOGITS
    0
    0.60
    r
    0.52
     Couples
    0.48
    5
    0.48
    共享
    0.46
    ave
    0.45
    args
    0.42
    hr
    0.42
    argon
    0.41
     Shared
    0.41
    Activations Density 0.000%

    No Known Activations