© 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. 182106
    Prev
    Next
    INDEX
    Explanations

    p-values < 0.001

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

    p-values and significance

    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
     Balmer
    0.47
     Compound
    0.45
     ∈
    0.45
    وبی
    0.43
     Unit
    0.43
     nucl
    0.42
     Tagen
    0.42
     Standard
    0.42
     Newtonsoft
    0.42
    羙
    0.42
    POSITIVE LOGITS
    ный
    0.49
     eso
    0.44
     эволю
    0.42
    eso
    0.42
     etcétera
    0.41
    uir
    0.41
    ]
    0.40
     pogod
    0.39
     иссле
    0.39
     proje
    0.39
    Activations Density 0.005%

    No Known Activations