© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113034
    Prev
    Next
    INDEX
    Explanations

    vera juice

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

    The neuron reliably activates on mentions of “aloe vera,” i.e. it picks out the phrase referring to the aloe vera plant.

    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
    ے
    -1.44
    espero
    -1.39
     desempen
    -1.39
     extrêmement
    -1.36
     at
    -1.36
     Pentru
    -1.35
    '
    -1.35
    زای
    -1.34
            
    -1.34
    र्शन
    -1.32
    POSITIVE LOGITS
    man
    1.84
    ัฒนา
    1.49
     hendes
    1.47
    that
    1.45
    but
    1.44
    甚至
    1.44
    vers
    1.43
    es
    1.43
     skol
    1.42
    wrights
    1.41
    Activations Density 0.000%

    No Known Activations