© 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. 104228
    Prev
    Next
    INDEX
    Explanations

    algae and algal

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

    terms related to algae and algal species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron consistently activates on various forms of “alga,” picking up occurrences of “alga,” “algae,” or “algal.”

    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
     However
    -3.17
     was
    -2.86
    ”
    -2.80
    但他
    -2.66
    缡
    -2.63
     Then
    -2.48
    随即
    -2.38
     confines
    -2.34
    ”،
    -2.25
    」
    -2.20
    POSITIVE LOGITS
    橚
    2.70
    gráficas
    2.48
    其他
    2.39
    ꒥
    2.34
    ࿙
    2.33
    凩
    2.28
     enamorado
    2.23
     当
    2.19
     were
    2.19
    ли
    2.14
    Activations Density 0.002%

    No Known Activations