© 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. 66783
    Prev
    Next
    INDEX
    Explanations

    companies, funds, early-stage, transport

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

    non-English text or technical terms

    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
     boasted
    0.53
     currency
    0.46
     দারিদ্র
    0.46
     brag
    0.46
     comme
    0.45
     如
    0.45
     populace
    0.43
     banknote
    0.43
     只
    0.43
     boasting
    0.43
    POSITIVE LOGITS
    経過
    0.49
    ርዝ
    0.46
    ਤ
    0.46
    しますが
    0.44
    と共に
    0.44
    стен
    0.44
    とな
    0.44
    繋
    0.43
     २०२२
    0.43
    ヘア
    0.43
    Activations Density 0.001%

    No Known Activations