© 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. 80066
    Prev
    Next
    INDEX
    Explanations

    interpolation and fitting

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

    The neuron fires strongly on occurrences of “interpol” (e.g. interpolation, interpolating, interpolate) and thus detects mentions of interpolation-related terms.

    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
     capucha
    -1.23
     maximale
    -1.22
     القديمة
    -1.21
    他
    -1.20
    ouder
    -1.18
    malte
    -1.17
    NewReader
    -1.17
     Tamanho
    -1.13
     זיי
    -1.13
     bied
    -1.13
    POSITIVE LOGITS
    </strong>
    1.31
     between
    1.28
     Interpolation
    1.26
    between
    1.23
    interpolation
    1.22
     crammed
    1.12
     techniques
    1.07
     NODE
    1.05
    仨
    1.05
    背后的
    1.04
    Activations Density 0.017%

    No Known Activations