© 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. 22-GEMMASCOPE-RES-131K
    7. 38586
    Prev
    Next
    INDEX
    Explanations

    what is valued

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

    The main thing this neuron does is detect the word “value” (and its close morphological variants such as “valuing,” “values,” etc.).

    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
     with
    -1.34
    ៍
    -1.29
     consciences
    -1.27
    akyti
    -1.24
     AppCompatTheme
    -1.22
    dengan
    -1.21
     illustrator
    -1.20
    Krishna
    -1.18
    鷙
    -1.17
     Anything
    -1.16
    POSITIVE LOGITS
    value
    1.53
     
    1.45
    more
    1.43
     being
    1.38
    would
    1.37
    worth
    1.35
     jako
    1.35
    lindung
    1.34
    these
    1.34
    </em>
    1.31
    Activations Density 0.021%

    No Known Activations