© 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. 47213
    Prev
    Next
    INDEX
    Explanations

    required analysis

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

    can followed by verbs or prepositions

    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
    when
    0.49
    她说
    0.48
    他说
    0.45
     όταν
    0.43
     When
    0.40
     благодар
    0.40
     when
    0.40
    当
    0.40
    ambil
    0.40
    intended
    0.40
    POSITIVE LOGITS
    해야
    0.49
     doivent
    0.49
    垶
    0.48
     분석
    0.46
     partake
    0.44
     해야
    0.43
     dilengkapi
    0.43
     직선
    0.42
     courbes
    0.41
     analys
    0.41
    Activations Density 0.000%

    No Known Activations