© 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. 110552
    Prev
    Next
    INDEX
    Explanations

    compound proper nouns

    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
     from
    -1.51
    because
    -1.38
     noticeably
    -1.30
     karena
    -1.20
     disconcer
    -1.16
     because
    -1.15
     Because
    -1.14
     their
    -1.13
     \{\
    -1.13
     relatively
    -1.11
    POSITIVE LOGITS
     –
    1.33
    當然
    1.18
     alcune
    1.09
    <b>
    1.09
     alguns
    1.05
    Bibliografie
    1.04
     molti
    1.02
    ’
    1.01
     ถ้า
    1.01
     watu
    1.00
    Activations Density 0.594%

    No Known Activations