© 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. 131764
    Prev
    Next
    INDEX
    Explanations

    specific follow-up phrases

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

    keywords for tech, programming, and concepts

    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
     świad
    0.63
     Swing
    0.50
     paysans
    0.50
     Navajo
    0.50
     фараз
    0.49
     candlelight
    0.48
     კ
    0.48
     entstanden
    0.48
     Köz
    0.48
    波动
    0.47
    POSITIVE LOGITS
    ків
    0.42
    AGON
    0.41
    ENTY
    0.40
    雫
    0.39
     সবাই
    0.39
    starter
    0.39
    ATIVE
    0.39
    ائط
    0.39
     mayoría
    0.38
    一款
    0.38
    Activations Density 0.000%

    No Known Activations