© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195504
    Prev
    Next
    INDEX
    Explanations

    incrementing or decrementing values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     switched
    0.50
     saves
    0.44
    蒐
    0.42
     secures
    0.41
     estates
    0.40
     filenames
    0.40
     timings
    0.40
     furnishings
    0.39
    낚
    0.39
    📷
    0.39
    POSITIVE LOGITS
     increment
    1.11
    Increment
    1.04
     increments
    1.00
     incremento
    1.00
    increment
    0.99
     Increment
    0.98
    increase
    0.96
    Increase
    0.95
     увеличение
    0.91
     decrement
    0.91
    Activations Density 0.066%

    No Known Activations