© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70898
    Prev
    Next
    INDEX
    Explanations

    as far as I know

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

    The neuron detects hedging or disclaimer phrases—especially occurrences of “as far as I know.”

    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
     musíte
    -1.20
     niektor
    -1.17
     můžete
    -1.11
     perhaps
    -1.10
     stroj
    -1.10
     reklama
    -1.09
     pozor
    -1.06
    fortawesome
    -1.05
     znal
    -1.05
     vám
    -1.05
    POSITIVE LOGITS
    only
    1.58
     nobody
    1.36
     there
    1.31
    never
    1.26
     no
    1.23
     only
    1.22
    there
    1.18
     haven
    1.17
    no
    1.15
    published
    1.11
    Activations Density 0.031%

    No Known Activations