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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177971
    Prev
    Next
    INDEX
    Explanations

    adverbs and descriptive suffixes

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

    often targets or exploits

    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_31_width_262k_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
    undle
    0.50
    टेगरी
    0.48
     ομάδα
    0.47
    娛樂
    0.44
    ocamp
    0.43
    Codigo
    0.43
    ள
    0.42
    रस
    0.42
     ടീ
    0.42
    厄
    0.42
    POSITIVE LOGITS
     hydrology
    0.43
     distort
    0.42
     metallurgy
    0.42
     agate
    0.42
     interwoven
    0.42
     windmills
    0.41
     dislocations
    0.40
     тексту
    0.40
     delim
    0.40
     values
    0.40
    Activations Density 0.001%

    No Known Activations