© 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. 4072
    Prev
    Next
    INDEX
    Explanations

    directly available/accessible/attributable

    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
     insgesamt
    0.69
     Juego
    0.61
     Obwohl
    0.57
     offizi
    0.56
    {
    0.56
     oficialmente
    0.54
     Trouvez
    0.53
     Incluso
    0.52
     Semoga
    0.52
    )$
    0.51
    POSITIVE LOGITS
     directly
    1.74
    directly
    1.66
    直接
    1.59
     Directly
    1.52
     direct
    1.45
     bezpośred
    1.44
     langsung
    1.43
     directamente
    1.38
     직접
    1.38
     напрямую
    1.34
    Activations Density 0.132%

    No Known Activations