© 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. 7647
    Prev
    Next
    INDEX
    Explanations

    Let's describe

    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
    י
    0.50
     élarg
    0.47
     contradd
    0.46
     azienda
    0.46
     centrales
    0.46
     hém
    0.46
    étend
    0.46
     azione
    0.45
     regola
    0.45
     vajj
    0.44
    POSITIVE LOGITS
     $
    0.43
     سوال
    0.43
     سؤال
    0.43
     pew
    0.43
     وصلنا
    0.42
     Board
    0.42
     الله
    0.41
     beberapa
    0.41
    SOL
    0.41
     Jennifer
    0.41
    Activations Density 0.000%

    No Known Activations