© 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. 161515
    Prev
    Next
    INDEX
    Explanations

    investment or competition

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

    representing the outcome

    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
    строй
    0.48
    łoży
    0.47
    стави
    0.47
    遗憾
    0.47
    日语
    0.47
     Temmuz
    0.46
     directa
    0.46
    逮
    0.46
     Sally
    0.45
     değildir
    0.45
    POSITIVE LOGITS
    investment
    0.49
    clim
    0.49
    romagnetic
    0.48
     ưu
    0.46
     phenotypic
    0.46
    preferred
    0.46
     پانچ
    0.46
    مند
    0.46
    necklace
    0.45
    deterministic
    0.45
    Activations Density 0.000%

    No Known Activations