© 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. 115758
    Prev
    Next
    INDEX
    Explanations

    divine economy, spent without, rotating rules

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

    business processes and productivity

    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
    shares
    0.46
    snapshots
    0.46
    ণা
    0.43
    reste
    0.43
    状
    0.42
    day
    0.41
    l
    0.41
    ｌ
    0.41
    SNAP
    0.40
    STEP
    0.40
    POSITIVE LOGITS
     trouv
    0.51
     европей
    0.50
     raconte
    0.50
     elucidate
    0.49
     Euclidean
    0.49
     extant
    0.47
    აძ
    0.47
     измере
    0.47
    NumConst
    0.47
     scă
    0.46
    Activations Density 0.000%

    No Known Activations