© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119017
    Prev
    Next
    INDEX
    Explanations

    quoted speech

    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
    ,''
    -1.13
     =
    -1.12
    」、「
    -1.10
    .,
    -1.09
    Says
    -1.08
    :
    -1.07
    (""),
    -1.05
    .“
    -1.03
    (''),
    -1.00
     ("
    -0.99
    POSITIVE LOGITS
    ↵↵
    1.41
     “…
    1.20
    PASO
    1.17
     "..
    1.02
    嬸
    1.00
     "...
    0.99
     "
    0.99
     añadió
    0.98
     “
    0.98
    ihnachts
    0.96
    Activations Density 0.011%

    No Known Activations