© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10799
    Prev
    Next
    INDEX
    Explanations

    political commentary criticizing figures

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

    The neuron flags strongly negative or critical language—pejorative adjectives and verbs used to attack or discredit.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Questão
    -1.33
     bambú
    -1.30
     possono
    -1.30
     maneiras
    -1.23
     géographie
    -1.20
     where
    -1.20
     gäller
    -1.19
    STUDIES
    -1.19
     keduanya
    -1.18
    ciuto
    -1.18
    POSITIVE LOGITS
    初め
    1.16
     It
    1.14
    self
    1.11
    entance
    1.07
     Contin
    1.06
     Removed
    1.05
    每个人
    1.04
    atting
    1.02
    ּוֹ
    1.02
     sel
    1.01
    Activations Density 0.102%

    No Known Activations