© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66713
    Prev
    Next
    INDEX
    Explanations

    suitable for a purpose

    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_10/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
     kurzem
    -1.78
     komplette
    -1.71
    燹
    -1.63
     двумя
    -1.63
    création
    -1.59
    diablo
    -1.59
     traditionelle
    -1.59
    蟜
    -1.58
    unches
    -1.55
    meow
    -1.55
    POSITIVE LOGITS
    the
    1.98
     you
    1.83
    O
    1.67
    of
    1.64
     When
    1.61
    You
    1.55
    E
    1.55
    以
    1.52
    such
    1.52
    U
    1.51
    Activations Density 0.009%

    No Known Activations