© 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. 33615
    Prev
    Next
    INDEX
    Explanations

    declaring new objects in code

    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
     ofere
    -1.32
     новой
    -1.13
     desfile
    -1.10
     balón
    -1.09
     подарки
    -1.05
    はある
    -1.05
     nieuwe
    -1.03
    Ủ
    -1.02
    を受け
    -1.02
     VOOR
    -1.02
    POSITIVE LOGITS
     from
    1.51
    ウィキ
    1.28
     Before
    1.12
     Although
    1.05
    évalu
    1.04
     From
    1.01
    From
    1.01
     very
    1.00
     sogenannten
    0.99
    طه
    0.98
    Activations Density 0.001%

    No Known Activations