© 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. 22-GEMMASCOPE-RES-131K
    4. 93294
    Prev
    Next
    INDEX
    Explanations

    wave vectors, momentum, and transforms

    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
     of
    -1.12
    %)$
    -1.09
     from
    -1.05
    鳄
    -1.02
     банков
    -1.01
    𝓐
    -1.01
    .
    -1.00
    “)
    -0.99
    >[
    -0.97
     anderen
    -0.96
    POSITIVE LOGITS
     příslu
    1.20
    ględ
    1.18
    uticos
    1.14
     हूं
    1.14
     scopo
    1.13
    argento
    1.10
     nuevamente
    1.10
     podremos
    1.09
    ómico
    1.09
    enderal
    1.07
    Activations Density 0.016%

    No Known Activations