© 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. 32419
    Prev
    Next
    INDEX
    Explanations

    replacing or renaming code elements

    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
     divisional
    0.42
    бычно
    0.41
    LEMN
    0.41
     Divisional
    0.41
    Chel
    0.40
    Strafpunkte
    0.40
    濕
    0.40
    loch
    0.40
    篙
    0.39
     ganzen
    0.39
    POSITIVE LOGITS
     rebranded
    0.64
     replaced
    0.60
     replaces
    0.59
     replacing
    0.58
     rename
    0.58
     rebranding
    0.57
     redefined
    0.55
     replace
    0.55
     renaming
    0.55
     renamed
    0.54
    Activations Density 0.047%

    No Known Activations