Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8898
    Prev
    Next
    INDEX
    Explanations

    prefixes and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siguiente
    -0.84
    смот
    -0.82
    imeter
    -0.71
    Expan
    -0.68
    Complaints
    -0.68
    Quir
    -0.67
    克服
    -0.67
    宣布
    -0.67
     putty
    -0.66
    Epide
    -0.66
    POSITIVE LOGITS
     op
    2.41
     loc
    1.99
    op
    1.99
    loc
    1.88
    Op
    1.68
     supra
    1.65
     cit
    1.61
     ibid
    1.61
     Op
    1.59
     aforementioned
    1.55
    Activations Density 0.013%

    No Known Activations