© 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. 39109
    Prev
    Next
    INDEX
    Explanations

    Soviet fleets, academic appeals, imagine

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

    initial, real, potential, strategy

    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
    現在は
    0.46
    potentially
    0.45
     指定
    0.45
    豪華
    0.45
    origine
    0.43
     popula
    0.43
    }$\
    0.42
     Fü
    0.41
    重新
    0.41
    miştir
    0.41
    POSITIVE LOGITS
    इंदौर
    0.46
     дві
    0.45
     memoir
    0.45
    ੪
    0.44
    igts
    0.44
    lept
    0.44
     inseparable
    0.44
    ạc
    0.43
     повинні
    0.43
     integrante
    0.42
    Activations Density 0.001%

    No Known Activations