© 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. 34-GEMMASCOPE-RES-131K
    7. 49706
    Prev
    Next
    INDEX
    Explanations

    weight gain

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

    The neuron activates on numeric quantitative measurements—especially weight/gain statistics (e.g. “weight 3840,” “gain 1184,” body‐weight values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Vorbe
    -0.66
     Wissenschaftler
    -0.65
    抽出
    -0.64
    VARI
    -0.64
    kro
    -0.64
     hopper
    -0.63
    MPN
    -0.63
    Pagamento
    -0.63
     tenemos
    -0.62
    いいですね
    -0.62
    POSITIVE LOGITS
     gain
    5.41
    gain
    4.59
     gains
    4.44
    Gain
    4.34
     gained
    4.31
     Gain
    4.28
     gaining
    3.91
     GAIN
    3.64
    GAIN
    3.64
     Gains
    3.50
    Activations Density 0.079%

    No Known Activations