© 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. 162640
    Prev
    Next
    INDEX
    Explanations

    prefixes and identifying words

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

    specific words or structural elements

    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
    罗斯
    0.43
    v
    0.41
    Circle
    0.41
     ඔබේ
    0.41
    দুল
    0.41
    斜
    0.40
    足以
    0.40
    nél
    0.38
    purge
    0.38
    槛
    0.38
    POSITIVE LOGITS
     nouns
    0.55
     जानेवारी
    0.50
     nominally
    0.47
    മ്പി
    0.46
     felonies
    0.45
    ◯
    0.45
    った
    0.45
    کومت
    0.44
     राइ
    0.43
     प्रिंट
    0.42
    Activations Density 0.002%

    No Known Activations