© 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. 32939
    Prev
    Next
    INDEX
    Explanations

    prepositions or conjunctions followed by pronouns

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

    Find information and next tokens

    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
    ጶ
    0.48
     electoral
    0.46
     cylindrical
    0.46
     perpetuate
    0.45
    parseDouble
    0.45
    んと
    0.45
     strikes
    0.44
     occupants
    0.44
     thorny
    0.44
     biometric
    0.43
    POSITIVE LOGITS
    bahan
    0.50
    kla
    0.47
     bahasa
    0.47
     menghasilkan
    0.47
    %).
    0.44
     نت
    0.44
     menghindari
    0.44
    wes
    0.44
    ler
    0.43
     gelesen
    0.43
    Activations Density 0.000%

    No Known Activations