© 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. 102663
    Prev
    Next
    INDEX
    Explanations

    publication for

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

    Retention Ratio

    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
    IT
    0.47
    聽
    0.44
    anske
    0.44
    ますが
    0.44
    IG
    0.43
    UM
    0.43
    OKR
    0.42
    </b>
    0.42
    ansk
    0.42
     функциони
    0.42
    POSITIVE LOGITS
     carelessly
    0.45
     üzerinde
    0.44
    톨
    0.44
     messageShow
    0.43
     поверхности
    0.43
    aceted
    0.43
     başında
    0.43
    רוי
    0.42
     überw
    0.42
    轍
    0.42
    Activations Density 0.001%

    No Known Activations