© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52565
    Prev
    Next
    INDEX
    Explanations

    X features and changes

    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_31_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
     easy
    0.45
    威胁
    0.44
     alarms
    0.43
     göz
    0.42
     escap
    0.42
     mech
    0.42
     *
    0.42
     log
    0.42
    \:
    0.42
    (*
    0.41
    POSITIVE LOGITS
    ليل
    0.50
     Vorteile
    0.46
    Б
    0.46
     funcionamiento
    0.45
    سبوع
    0.43
     даты
    0.43
    пил
    0.43
    чи
    0.42
     রিলি
    0.42
    Ј
    0.42
    Activations Density 0.007%

    No Known Activations