© 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. 12848
    Prev
    Next
    INDEX
    Explanations

    real estate listings

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

    ranking systems and names

    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
     fucking
    0.33
    🤬
    0.32
    🧠
    0.31
     psychotherapy
    0.30
     facilitation
    0.30
     literacy
    0.30
     वंचित
    0.29
    🕌
    0.29
     reserv
    0.29
     👀
    0.29
    POSITIVE LOGITS
     मेटल
    0.33
     Alsace
    0.32
    Lac
    0.32
     Tipo
    0.32
    gean
    0.31
    oll
    0.31
    ্রে
    0.31
    ị
    0.31
     bagian
    0.31
     H
    0.30
    Activations Density 0.001%

    No Known Activations