© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98431
    Prev
    Next
    INDEX
    Explanations

    notnot neednot impossiblenot arisenot will be

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

    The neuron detects Russian negation words (e.g. “не,” “нельзя”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     or
    -1.43
     not
    -1.28
     only
    -1.25
     році
    -1.18
     some
    -1.16
    vidades
    -1.16
     mosaico
    -1.15
     fön
    -1.13
     elefante
    -1.12
    tanaman
    -1.11
    POSITIVE LOGITS
    任何
    1.34
     anything
    1.33
    有任何
    1.32
     "
    1.17
     et
    1.16
    ceptives
    1.13
     anymore
    1.06
    formed
    1.06
     подоб
    1.06
     nawet
    1.04
    Activations Density 0.014%

    No Known Activations