© 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. 117682
    Prev
    Next
    INDEX
    Explanations

    non-profit organization types

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

    non-profit

    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
    ាតុ
    0.55
    훑
    0.51
     நீரில்
    0.49
    찧
    0.48
    <unused401>
    0.48
    біць
    0.47
    гры
    0.47
     оки
    0.46
    ㄶ
    0.46
    гр
    0.46
    POSITIVE LOGITS
     levant
    0.53
    )
    0.51
    ni
    0.51
    ci
    0.50
    eri
    0.50
     atelier
    0.50
    ake
    0.50
     sugger
    0.49
     doppio
    0.49
    dej
    0.48
    Activations Density 0.005%

    No Known Activations