© 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. 34-GEMMASCOPE-RES-131K
    7. 108007
    Prev
    Next
    INDEX
    Explanations

    plunged, plunged into

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

    This neuron responds strongly to very common, high‐frequency tokens (e.g., frequent function words and broadly used terms).

    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
    և
    -0.84
     Himmels
    -0.73
     Quadrant
    -0.71
     PID
    -0.70
     Ria
    -0.68
     stimulated
    -0.68
    foglal
    -0.66
     kabupaten
    -0.66
     hampered
    -0.66
    tring
    -0.66
    POSITIVE LOGITS
     plunged
    4.03
     plunge
    3.63
     plunging
    3.33
     plung
    3.22
     Plung
    2.88
     погру
    2.48
     plonge
    2.05
     mergul
    1.91
     immersion
    1.84
     immerse
    1.83
    Activations Density 0.055%

    No Known Activations