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. 7666
    Prev
    Next
    INDEX
    Explanations

    properties and studies

    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
     invariably
    -1.26
     quienes
    -1.15
    OkHttpClient
    -1.06
     unduly
    -1.01
     deliberations
    -1.00
    ◇
    -0.98
    десь
    -0.98
     superbly
    -0.97
     viceversa
    -0.97
    动静
    -0.96
    POSITIVE LOGITS
     adaptable
    0.98
     welches
    0.91
     concerning
    0.89
     beforehand
    0.86
     данного
    0.84
     supposed
    0.84
     особен
    0.82
     stated
    0.82
     possessing
    0.81
     данный
    0.81
    Activations Density 0.166%

    No Known Activations