© 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. 118977
    Prev
    Next
    INDEX
    Explanations

    expensive items or activities

    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
    安い
    -1.13
     imposs
    -1.10
     abolished
    -1.03
     inexpensive
    -0.99
     renamed
    -0.93
     esque
    -0.92
     decidi
    -0.92
     Ответить
    -0.91
     adresses
    -0.91
     दौरान
    -0.90
    POSITIVE LOGITS
     ($
    1.99
    ($
    1.53
     (£
    1.38
     option
    1.35
     options
    1.23
     but
    1.14
     upkeep
    1.13
     (>
    1.09
     proposition
    1.08
     item
    1.05
    Activations Density 0.024%

    No Known Activations