© 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. 26030
    Prev
    Next
    INDEX
    Explanations

    stages, tiers, rounds, chapters, periods, phases, storeys

    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
     from
    -1.27
     their
    -1.16
     acreditar
    -1.08
    from
    -1.03
     bambina
    -0.99
     those
    -0.97
     leggera
    -0.96
     noticed
    -0.95
    oxone
    -0.95
     or
    -0.94
    POSITIVE LOGITS
     of
    1.60
    INATION
    1.13
    媖
    1.11
     nativo
    1.10
     COMPOUNDS
    1.09
     lente
    1.09
    ecks
    1.08
     preacher
    1.05
     corrom
    1.05
     serre
    1.05
    Activations Density 0.062%

    No Known Activations