© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9889
    Prev
    Next
    INDEX
    Explanations

    when or nowadays

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

    model response headers or introductory phrases

    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
     specifica
    0.25
    Მ
    0.23
     alleles
    0.23
     commandes
    0.23
     pronouns
    0.23
    듈
    0.22
     noyau
    0.22
    讵
    0.22
    ेंटल
    0.22
    Ა
    0.22
    POSITIVE LOGITS
     요즘
    0.28
    When
    0.27
    Imagine
    0.27
     Imagine
    0.25
     आजकल
    0.25
    近年
    0.23
     যখন
    0.23
    เมื่อ
    0.23
     когда
    0.23
     عندما
    0.23
    Activations Density 0.178%

    No Known Activations