© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205033
    Prev
    Next
    INDEX
    Explanations

    word definition query

    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_262k_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
    茁
    0.48
     lớ
    0.45
     diploid
    0.41
    㴦
    0.39
    iscale
    0.38
    كان
    0.38
     دوباره
    0.38
     avanzado
    0.38
    ція
    0.37
     inan
    0.37
    POSITIVE LOGITS
     прави
    0.38
     Оста
    0.38
    0.38
     P
    0.37
     Leer
    0.36
     mysqli
    0.35
     Dirty
    0.34
    ...
    0.33
     Onder
    0.33
     อนุ
    0.33
    Activations Density 0.001%

    No Known Activations