© 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. 65568
    Prev
    Next
    INDEX
    Explanations

    prefixes followed by technical terms

    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
     ativar
    -1.06
     weißem
    -1.02
    uroy
    -0.96
     vozid
    -0.96
    Garantía
    -0.95
    鈑
    -0.94
    ᕙ
    -0.94
    RESULTADOS
    -0.91
    Codice
    -0.91
     noastră
    -0.91
    POSITIVE LOGITS
     all
    1.05
     of
    1.02
    V
    0.92
    O
    0.91
    D
    0.90
    นำ
    0.89
    r
    0.88
    """
    0.88
    gers
    0.88
    l
    0.85
    Activations Density 0.014%

    No Known Activations