© 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. 104229
    Prev
    Next
    INDEX
    Explanations

    determines their purpose

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

    often requires

    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
     vous
    0.42
    ls
    0.41
     tienes
    0.41
     شنو
    0.41
    ((-
    0.39
    fält
    0.39
    кугӀ
    0.39
     plantea
    0.39
    pro
    0.38
     Você
    0.38
    POSITIVE LOGITS
    Aeonium
    0.45
    เน
    0.44
     서로
    0.44
     दामों
    0.44
    𝕣
    0.44
    กัน
    0.43
     uncorrelated
    0.43
    癀
    0.43
    玛
    0.43
    一层
    0.42
    Activations Density 0.002%

    No Known Activations