© 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. 91874
    Prev
    Next
    INDEX
    Explanations

    related to

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

    definition of 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
     comércio
    0.47
     वग
    0.45
     pedibusque
    0.44
    𒌍
    0.44
     exo
    0.44
     producers
    0.43
     expatri
    0.43
     perdagangan
    0.43
     आणि
    0.43
     traders
    0.43
    POSITIVE LOGITS
    يهه
    0.48
    že
    0.45
    votes
    0.45
    ב
    0.45
    Adams
    0.42
    Loved
    0.41
     Adams
    0.41
    الله
    0.40
    ואה
    0.40
    버지
    0.40
    Activations Density 0.002%

    No Known Activations