© 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. 80949
    Prev
    Next
    INDEX
    Explanations

    names joined by and

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ),
    -1.29
    Kullan
    -1.16
    演員
    -1.12
     pán
    -1.09
     matières
    -1.05
    Señor
    -1.04
     mouvements
    -1.04
     quartiers
    -1.00
    Otras
    -1.00
     besoins
    -1.00
    POSITIVE LOGITS
     his
    2.28
     I
    1.23
     DÍA
    1.06
     himself
    1.04
     him
    1.02
     myself
    1.02
     उसकी
    1.00
     COMERC
    0.99
     Accesorios
    0.98
     transferir
    0.96
    Activations Density 0.024%

    No Known Activations