© 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. 10-GEMMASCOPE-RES-131K
    7. 101452
    Prev
    Next
    INDEX
    Explanations

    guarantee or promise

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

    The neuron detects occurrences of the root “guarantee” (including “guarantee,” “guarantees,” “guaranteed,” etc.) in text.

    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
     vientos
    -1.63
     hinzugefügt
    -1.50
     onlar
    -1.48
     dinosaurio
    -1.43
     crafty
    -1.41
     отличаются
    -1.41
    vierung
    -1.35
     uwag
    -1.35
    bebasan
    -1.34
    ならでは
    -1.34
    POSITIVE LOGITS
     your
    1.40
     what
    1.34
     cæ
    1.30
     how
    1.30
     Programm
    1.27
    场景
    1.23
     obt
    1.23
     decorativo
    1.20
     Vergine
    1.20
     decorativa
    1.19
    Activations Density 0.027%

    No Known Activations