© 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. 41172
    Prev
    Next
    INDEX
    Explanations

    periods, makes, items

    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
     state
    0.48
     authentication
    0.46
     zone
    0.45
     bidders
    0.45
     signature
    0.44
     defense
    0.43
    ties
    0.42
    8
    0.42
     State
    0.41
    7
    0.41
    POSITIVE LOGITS
     එය
    0.52
     Hacer
    0.51
     włas
    0.50
     compreender
    0.50
    ഹ
    0.49
     împre
    0.49
     ඔහු
    0.48
     Álvaro
    0.48
     Lobkovic
    0.48
    ແ
    0.48
    Activations Density 0.000%

    No Known Activations