© 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. 138604
    Prev
    Next
    INDEX
    Explanations

    buying a new home

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

    actions after input

    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
    '
    0.51
    enton
    0.46
    ']
    0.46
    ]
    0.46
    ל
    0.46
    Enumer
    0.45
     ake
    0.45
    скохозяй
    0.45
    .'
    0.45
     Yield
    0.45
    POSITIVE LOGITS
    値
    0.52
    ሳት
    0.51
     specifica
    0.48
     crashes
    0.46
     défaut
    0.46
    ждает
    0.46
     confuses
    0.46
     meshes
    0.45
    ﺪ
    0.45
    فاوت
    0.45
    Activations Density 0.001%

    No Known Activations