© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55586
    Prev
    Next
    INDEX
    Explanations

    historically used or formerly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     అంటున్నారు
    0.41
    proving
    0.39
    不要
    0.38
     needn
    0.37
    ዕ
    0.37
    ᒪ
    0.37
    倛
    0.35
    のではなく
    0.35
    ລ
    0.35
     માં
    0.35
    POSITIVE LOGITS
     এতদিন
    1.15
     historically
    1.10
     Historically
    1.03
    當時
    1.02
     traditionally
    1.01
     była
    1.01
     formerly
    1.00
    当时
    1.00
     buvo
    1.00
     previously
    0.98
    Activations Density 0.190%

    No Known Activations