© 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-262K
    7. 112
    Prev
    Next
    INDEX
    Explanations

    variables, integers, derivatives

    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_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
    錬
    0.45
     :\
    0.44
    ಿಗೆ
    0.43
     </>
    0.43
    iją
    0.42
     યોગ
    0.42
    번에
    0.41
    :‏
    0.41
     सदी
    0.41
    Telecom
    0.41
    POSITIVE LOGITS
     has
    0.47
    textAllCaps
    0.44
     catatan
    0.42
     elegance
    0.41
     researcher
    0.40
     accentuated
    0.40
    存在する
    0.39
     dashing
    0.39
     incomplete
    0.39
     sceptical
    0.38
    Activations Density 0.005%

    No Known Activations