© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3107
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    specific attributes of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ``
    0.37
    <0xE2>
    0.35
     .......
    0.31
    .........
    0.30
     fi
    0.29
    ......
    0.29
     ......
    0.29
    𒐪
    0.29
     ...
    0.29
     ...(
    0.29
    POSITIVE LOGITS
     shitty
    0.59
     crappy
    0.59
     asshole
    0.47
     stupid
    0.45
     stupidity
    0.45
     picky
    0.44
     weird
    0.43
     idiots
    0.43
     laziness
    0.43
     craziness
    0.42
    Activations Density 0.941%

    No Known Activations