© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11960
    Prev
    Next
    INDEX
    Explanations

    numbers and the word 'eight'

    np_acts-logits-general · gemini-2.5-flash-lite

    eighth wonder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㑨
    0.42
     nigg
    0.38
     displacements
    0.38
    可持续
    0.38
    दायी
    0.38
     supposition
    0.37
    '});
    0.37
     제곱
    0.37
     sweetest
    0.37
    单击
    0.37
    POSITIVE LOGITS
    8
    0.48
    2
    0.46
    utos
    0.45
     आठ
    0.45
     восем
    0.45
    撮影
    0.44
     ocho
    0.43
    eight
    0.42
    rational
    0.39
    textview
    0.39
    Activations Density 0.206%

    No Known Activations