© 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. 9775
    Prev
    Next
    INDEX
    Explanations

    probability distributions and functions

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

    The neuron activates on occurrences of the word “exponential” (e.g. exponential distributions, exponential functions, exponential moving average).

    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
     alcune
    -1.15
    ほとん
    -1.14
    щите
    -1.13
     xadrez
    -1.13
     siè
    -1.12
     afront
    -1.09
     grandiose
    -1.07
     palha
    -1.06
    ellants
    -1.06
     japan
    -1.03
    POSITIVE LOGITS
     with
    1.83
     will
    1.36
     their
    1.30
     on
    1.25
     $
    1.24
     for
    1.24
     model
    1.23
     we
    1.20
     our
    1.17
     as
    1.16
    Activations Density 0.065%

    No Known Activations