© 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. 123471
    Prev
    Next
    INDEX
    Explanations

    providing context after certain phrases

    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
    v
    0.53
     No
    0.44
     NO
    0.44
    p
    0.42
     Ly
    0.41
     giãn
    0.41
     tried
    0.40
    awy
    0.40
     Liability
    0.39
     komunik
    0.38
    POSITIVE LOGITS
     любой
    0.51
    ሆ
    0.49
     foal
    0.49
     положения
    0.48
     осень
    0.47
     headway
    0.47
    ਲਾਂ
    0.47
     कहानी
    0.46
    arzys
    0.46
    Ottawa
    0.45
    Activations Density 0.002%

    No Known Activations