Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41111
    Prev
    Next
    INDEX
    Explanations

    factors affecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     факторов
    1.50
    factors
    1.48
     факторы
    1.40
     FACTORS
    1.31
     factors
    1.29
    𝘺
    1.26
     fattori
    1.26
     fatores
    1.20
     factions
    1.18
    𝘧
    1.16
    POSITIVE LOGITS
    в
    1.13
    времен
    1.11
     integrante
    1.03
     comprim
    1.02
    ر
    0.97
     arranque
    0.96
     recob
    0.95
     entr
    0.93
    ্দ
    0.91
     común
    0.90
    Activations Density 0.029%

    No Known Activations