© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13677
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     compacto
    0.57
     মিলিত
    0.56
     striking
    0.55
     pintar
    0.53
    พิ
    0.53
     tecnologia
    0.52
     Stri
    0.50
    ﻌ
    0.50
     Buddha
    0.49
     කු
    0.49
    POSITIVE LOGITS
    anns
    0.60
    evo
    0.58
    elman
    0.58
    isors
    0.57
    ippings
    0.57
    Amin
    0.57
    ത്തന
    0.56
    kans
    0.55
    adisu
    0.55
    annis
    0.55
    Activations Density 0.000%

    No Known Activations