© 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. 74573
    Prev
    Next
    INDEX
    Explanations

    replacements and new roles

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

    replacement, substitute, transition

    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
     भेदभाव
    0.42
    চক
    0.40
    reducible
    0.40
     रग
    0.40
     ફરિયાદ
    0.40
    domains
    0.39
     domains
    0.39
    瘩
    0.39
    ड़का
    0.38
     যুক্ত
    0.38
    POSITIVE LOGITS
     replacements
    1.16
     replacement
    1.09
     Replacement
    1.03
     replace
    0.96
    replacement
    0.95
     replaces
    0.94
     replacing
    0.93
     substitutes
    0.93
     sostit
    0.93
     substitu
    0.92
    Activations Density 0.201%

    No Known Activations