© 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. 104324
    Prev
    Next
    INDEX
    Explanations

    thread, post, title, announcement

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

    redundancy

    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
    -
    0.57
     स्टैंड
    0.51
    २
    0.46
    特別な
    0.44
    yaa
    0.43
    ายุ
    0.43
    手機
    0.43
    𝕦
    0.42
     फ़
    0.42
    🍆
    0.42
    POSITIVE LOGITS
     bereits
    0.47
     Grundlage
    0.45
    ेशनों
    0.44
     redundancy
    0.42
    Questa
    0.42
     Cedar
    0.41
     tellus
    0.41
    看过
    0.41
     veck
    0.41
     Infiniti
    0.41
    Activations Density 0.001%

    No Known Activations