© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    also + subject + action

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

    also, in addition

    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
     nějak
    0.54
     quoique
    0.46
     crappy
    0.45
     bzw
    0.44
     oder
    0.44
     murky
    0.44
     campeonato
    0.43
    呃
    0.43
     alebo
    0.42
     crap
    0.42
    POSITIVE LOGITS
     также
    1.22
     also
    1.19
    also
    1.07
     також
    1.07
     inoltre
    1.06
     ayrıca
    1.05
     همچنین
    1.03
     también
    0.95
     myös
    0.95
     таксама
    0.95
    Activations Density 0.455%

    No Known Activations