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. 8745
    Prev
    Next
    INDEX
    Explanations

    Posts Tagged

    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
    اسخ
    -0.77
     Verlust
    -0.75
    hyun
    -0.75
     burden
    -0.74
    şme
    -0.73
     fascinating
    -0.71
     Weit
    -0.71
     citta
    -0.71
    ματος
    -0.71
    auth
    -0.70
    POSITIVE LOGITS
    “
    1.03
     “...
    0.99
     “
    0.98
    “,
    0.91
     “(
    0.89
     “.
    0.85
     (“
    0.85
    “(
    0.82
    ,“
    0.81
     “[
    0.80
    Activations Density 0.194%

    No Known Activations