© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46571
    Prev
    Next
    INDEX
    Explanations

    URLsURLs and web addresses

    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_16_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
    a
    0.61
    r
    0.60
     He
    0.54
    h
    0.50
    ே
    0.50
    ా
    0.50
    an
    0.49
     Phrase
    0.49
    s
    0.49
    /**
    0.48
    POSITIVE LOGITS
     graduellement
    0.52
     مختلفة
    0.51
     unquestionably
    0.46
     那麼
    0.46
    łym
    0.45
     estuaries
    0.45
     بودند
    0.43
     progressivement
    0.42
     journalistic
    0.42
    ábamos
    0.42
    Activations Density 0.001%

    No Known Activations