© 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. 10-GEMMASCOPE-RES-131K
    7. 40523
    Prev
    Next
    INDEX
    Explanations

    telephony

    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_10/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
    '
    -2.20
     gesamten
    -2.20
     speziellen
    -2.11
    を作る
    -2.05
     wenige
    -2.00
     einzigen
    -1.98
    甭
    -1.98
    鬭
    -1.98
     eigentlichen
    -1.89
     ''
    -1.88
    POSITIVE LOGITS
    {
    2.47
    s
    2.33
    ]
    2.30
    <
    2.19
    也是
    2.16
    但
    2.16
    ftrag
    2.14
    нутрен
    2.09
     musik
    2.08
     اشار
    2.08
    Activations Density 0.003%

    No Known Activations