© 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. 235907
    Prev
    Next
    INDEX
    Explanations

    cigarette hygiene, hand hygiene

    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
     handling
    0.47
     handled
    0.45
     subjected
    0.45
     treated
    0.44
    ressed
    0.41
     logging
    0.40
    '
    0.40
     resemblance
    0.39
    =
    0.39
    en
    0.39
    POSITIVE LOGITS
    িনের
    0.54
     поиск
    0.51
    হাস
    0.50
     неизвест
    0.50
     Fähigkeiten
    0.50
    বর্তমানে
    0.50
     સત
    0.50
    izlik
    0.50
     पीएफआई
    0.50
     кін
    0.50
    Activations Density 0.001%

    No Known Activations