© 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. 33770
    Prev
    Next
    INDEX
    Explanations

    paths and file names

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

    source code directories

    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
     smoothly
    0.40
     distintos
    0.39
     calmer
    0.39
     draining
    0.38
     smoothies
    0.38
     càng
    0.38
     และ
    0.38
     ⋮
    0.37
     luminos
    0.37
    +"\
    0.36
    POSITIVE LOGITS
    7
    0.50
    បន្ទ
    0.48
    8
    0.47
     Michaelmas
    0.46
    6
    0.46
    9
    0.45
    История
    0.45
    usian
    0.45
    Storia
    0.45
     Algon
    0.44
    Activations Density 0.000%

    No Known Activations