© 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. 10790
    Prev
    Next
    INDEX
    Explanations

    business, technology, operations

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

    key terms introducing explanations

    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
     to
    0.32
     with
    0.32
     which
    0.30
     for
    0.29
    х
    0.28
    ファイルの
    0.27
     including
    0.27
     of
    0.27
    -,
    0.27
    -
    0.26
    POSITIVE LOGITS
    Bechyné
    0.27
    就知道
    0.26
    Begriffsklär
    0.25
    lblCredits
    0.25
    )
    0.24
    」
    0.24
    OrCallback
    0.23
     úspě
    0.23
    Ⲓ
    0.23
    estly
    0.22
    Activations Density 0.098%

    No Known Activations