© 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. 109772
    Prev
    Next
    INDEX
    Explanations

    growing followed by nouns of increase

    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
     LIABLE
    -1.07
    surfing
    -1.02
    varying
    -0.99
    varies
    -0.98
    ier
    -0.98
    increases
    -0.96
     sprend
    -0.92
     puntuación
    -0.91
    zzled
    -0.89
    fertigt
    -0.89
    POSITIVE LOGITS
     number
    1.84
     popularity
    1.45
     demands
    1.34
     awareness
    1.31
     trend
    1.28
     число
    1.28
     importance
    1.24
     concern
    1.23
     pains
    1.22
     interest
    1.20
    Activations Density 0.047%

    No Known Activations