© 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. 22-GEMMASCOPE-RES-131K
    7. 73507
    Prev
    Next
    INDEX
    Explanations

    JavaScript configuration objects

    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_22/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
     gefüllt
    -1.54
     войск
    -1.30
     моей
    -1.25
    cznej
    -1.21
     میکنم
    -1.16
     bedeckt
    -1.15
     verarbeitet
    -1.14
     gegangen
    -1.13
     stück
    -1.13
     from
    -1.12
    POSITIVE LOGITS
     their
    1.75
    ﻷ
    1.40
    ﻹ
    1.35
     cerveza
    1.12
     ۲۰۰
    1.09
    HDD
    1.09
    ׇ
    1.09
    @^
    1.08
    зал
    1.06
    –
    1.06
    Activations Density 0.018%

    No Known Activations