© 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. 79402
    Prev
    Next
    INDEX
    Explanations

    opinion polls

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

    single, one or piece

    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
    partner
    0.48
    line
    0.47
    pert
    0.46
    lem
    0.45
    ν
    0.45
    persist
    0.44
    well
    0.44
    quement
    0.43
    呢
    0.43
    副
    0.42
    POSITIVE LOGITS
     言っ
    0.52
     divs
    0.49
     நூ
    0.48
     заряда
    0.48
     NTFS
    0.48
     vijj
    0.46
    ॉफ्ट
    0.45
     отметил
    0.45
     適
    0.45
    وسیع
    0.45
    Activations Density 0.001%

    No Known Activations