© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14392
    Prev
    Next
    INDEX
    Explanations

    it is often followed by 'is' or 'was'which is followed by a verb or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    えっ
    -1.09
    ブログ村
    -1.05
    molde
    -1.05
    ほら
    -1.05
     mnoho
    -1.02
    *{-
    -1.01
    Kleur
    -1.00
     flamboyant
    -1.00
    ビックリ
    -0.99
     étudier
    -0.99
    POSITIVE LOGITS
     has
    1.16
    stem
    1.00
     taken
    0.94
     first
    0.94
     where
    0.92
    Stem
    0.91
     comes
    0.91
     occur
    0.89
     doing
    0.88
     Отечественной
    0.86
    Activations Density 0.167%

    No Known Activations