© 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. 10-GEMMASCOPE-RES-131K
    4. 75279
    Prev
    Next
    INDEX
    Explanations

    fix, purify, correct errors

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

    The neuron spikes on technical action verbs—especially process-oriented words (e.g. purifies, compressing, reorienting, calibrating)—marking descriptions of operations or modifications.

    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
     to
    -2.38
     with
    -1.43
    amzn
    -1.34
     by
    -1.32
    >{@
    -1.30
     in
    -1.26
    ৄ
    -1.25
    的一切
    -1.22
     começo
    -1.22
    Bong
    -1.20
    POSITIVE LOGITS
    を見ながら
    1.59
     moléculas
    1.44
    done
    1.40
     agujeros
    1.38
     paroi
    1.36
     empêcher
    1.34
     XXIX
    1.31
     exercice
    1.30
    她的
    1.28
     JpaRepository
    1.27
    Activations Density 0.207%

    No Known Activations