© 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. 71109
    Prev
    Next
    INDEX
    Explanations

    financial or sensitive information

    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
    reuses
    0.45
     prices
    0.44
    น
    0.43
    ophenone
    0.42
    avourites
    0.41
     says
    0.41
     announcements
    0.40
     jeder
    0.40
     त्यो
    0.40
    ag
    0.39
    POSITIVE LOGITS
     initiator
    0.52
     Probation
    0.48
     അന്വേഷ
    0.47
    ﻪ
    0.47
    ྞ
    0.46
     assessor
    0.46
     stipend
    0.45
    图中
    0.44
    ʑ
    0.43
     জানতে
    0.43
    Activations Density 0.006%

    No Known Activations