© 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. 30912
    Prev
    Next
    INDEX
    Explanations

    dictionary keys or hash table keys

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

    dictionary keys

    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
    ાગ
    0.42
    त्याने
    0.42
     EdgeInsets
    0.42
    𝕠
    0.42
    ₆
    0.40
     சுற்றுலா
    0.40
    กอง
    0.39
    attva
    0.39
    秥
    0.39
     Virgen
    0.38
    POSITIVE LOGITS
    Keys
    0.50
     Keys
    0.49
     keys
    0.48
    keySet
    0.45
    keys
    0.44
     key
    0.43
     dict
    0.43
     Delivering
    0.42
     lanes
    0.41
     Dict
    0.41
    Activations Density 0.000%

    No Known Activations