© 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. 34-GEMMASCOPE-RES-131K
    4. 92445
    Prev
    Next
    INDEX
    Explanations

    `#include` following certain tokens

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

    The neuron is keyed to numeric tokens (i.e. sequences of digits).

    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
    Pardon
    -0.73
     superstructure
    -0.64
    ggard
    -0.63
    ようで
    -0.63
     pivo
    -0.63
     perchance
    -0.61
    アーカイブ
    -0.61
    ﻛ
    -0.60
    選手権
    -0.60
    لیت
    -0.60
    POSITIVE LOGITS
     tüm
    0.69
     Zusammen
    0.68
    isDefault
    0.68
     εί
    0.67
     automotive
    0.66
     comunidad
    0.66
     zrobić
    0.65
     corneal
    0.64
    two
    0.64
    energy
    0.64
    Activations Density 0.101%

    No Known Activations