© 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. 64724
    Prev
    Next
    INDEX
    Explanations

    increasingly in diverse applications

    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
    ագր
    0.44
    Cidade
    0.43
    ኻ
    0.41
    이기
    0.39
    すると
    0.38
     سلاټ
    0.37
     Adapun
    0.37
    Entonces
    0.37
    ሂ
    0.37
    ともに
    0.37
    POSITIVE LOGITS
     included
    0.52
     SAFETY
    0.50
     (
    0.47
     Sicherheits
    0.46
    SAFETY
    0.46
     சுற்றுச்சூழ
    0.45
     includes
    0.45
     Safety
    0.45
    included
    0.44
    ,
    0.44
    Activations Density 0.009%

    No Known Activations