© 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. 27483
    Prev
    Next
    INDEX
    Explanations

    explaining definitions or how phrases work

    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
    які
    0.43
     వెంట
    0.43
    ወቅ
    0.42
     innovations
    0.41
     infrastrukt
    0.40
    倹
    0.40
     menghub
    0.38
     инфраструк
    0.38
     먼
    0.38
     ಸರಿಯ
    0.38
    POSITIVE LOGITS
     décision
    0.50
     culoare
    0.45
     decisão
    0.44
     तुम्ही
    0.44
     purportedly
    0.44
     herself
    0.43
     decyz
    0.43
     guise
    0.43
     decisión
    0.43
     comunque
    0.42
    Activations Density 0.024%

    No Known Activations