© 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. 63590
    Prev
    Next
    INDEX
    Explanations

    Indian names and Sanskrit terms

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

    This neuron detects romanized Sanskrit words and multi‐syllable Sanskrit morphemes.

    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
     initializing
    -0.91
    文化財
    -0.89
     globale
    -0.85
    temple
    -0.83
    レビュー
    -0.83
     Publikum
    -0.83
     kor
    -0.82
     statut
    -0.82
    şme
    -0.81
     palme
    -0.81
    POSITIVE LOGITS
    ••
    0.96
    ZONE
    0.93
    anya
    0.93
     aceea
    0.92
    ••••
    0.89
    にくい
    0.88
    きち
    0.88
    hater
    0.86
     スポーツ
    0.85
     काफी
    0.85
    Activations Density 0.022%

    No Known Activations