© 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. 64684
    Prev
    Next
    INDEX
    Explanations

    words starting with h

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

    The neuron activates on numeric tokens (sequences of digits), i.e. it detects numbers.

    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
     Arzne
    -0.74
    ator
    -0.71
    كونات
    -0.69
     established
    -0.68
     apt
    -0.68
     století
    -0.67
     snug
    -0.66
     excellent
    -0.65
    zh
    -0.64
     лекар
    -0.64
    POSITIVE LOGITS
     Hydrogen
    1.35
     Heroes
    1.22
    Hydrogen
    1.19
     Horizons
    1.18
     Hydra
    1.16
    Hydraulic
    1.16
     hexagon
    1.15
     Holo
    1.13
     Hydraulic
    1.12
     Hypothesis
    1.12
    Activations Density 0.046%

    No Known Activations