© 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. 4723
    Prev
    Next
    INDEX
    Explanations

    some or certain words

    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
     quelcon
    0.38
     ות
    0.35
    Processes
    0.34
     процессов
    0.33
     остальные
    0.33
    这一切
    0.32
     ANYTHING
    0.31
     您
    0.31
     остальных
    0.31
    Ს
    0.30
    POSITIVE LOGITS
     certain
    0.42
    ,
    0.38
     sommige
    0.37
     algunas
    0.36
     بعض
    0.35
     arguably
    0.34
     certains
    0.34
     niektó
    0.34
     vissa
    0.33
     alguns
    0.33
    Activations Density 0.144%

    No Known Activations