© 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-262K
    7. 45142
    Prev
    Next
    INDEX
    Explanations

    census Chinese aims

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

    Pig Latin translations

    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_262k_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
     o
    0.51
     „
    0.49
    )
    0.49
     \
    0.48
     ㅇ
    0.46
     ET
    0.45
     FCA
    0.45
     የግ
    0.44
     Siberian
    0.44
     ‚
    0.44
    POSITIVE LOGITS
    ൪
    0.57
     atacar
    0.53
     tasmim
    0.52
     selecionar
    0.52
    зать
    0.51
    痢
    0.51
    ▩
    0.51
    analisi
    0.50
    atoti
    0.50
     progetto
    0.50
    Activations Density 0.000%

    No Known Activations