© 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. 58824
    Prev
    Next
    INDEX
    Explanations

    therm and sperm

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

    The neuron detects words with the prefix "therm" such as "thermodynamic," "thermoplastic," and "thermophilic," along with some biological terms related to reproduction like "sperm."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ا
    -2.59
    在他的
    -2.53
     treacherous
    -2.47
     многих
    -2.30
    してます
    -2.28
    鹩
    -2.27
     “
    -2.25
    出来る
    -2.23
     которой
    -2.23
    頂き
    -2.20
    POSITIVE LOGITS
    h
    2.88
    ଝ
    2.84
    ON
    2.58
    s
    2.58
    ⽼
    2.55
    獁
    2.45
    o
    2.42
     内衣
    2.34
    Y
    2.31
     pemasaran
    2.30
    Activations Density 0.020%

    No Known Activations