© 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. 47038
    Prev
    Next
    INDEX
    Explanations

    mermaids eggs duck

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

    Okay, let's talk

    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
    Გ
    0.53
    ká
    0.52
    is
    0.52
     as
    0.52
     প্য
    0.51
     يُ
    0.50
     تُ
    0.48
     cá
    0.47
    𝖓
    0.47
     Winds
    0.47
    POSITIVE LOGITS
    voerd
    0.48
     nascita
    0.43
     बध
    0.41
    响应文件
    0.41
    δρο
    0.40
    ες
    0.40
     निगरानी
    0.40
    ımızı
    0.40
     idiosyncratic
    0.40
    ılması
    0.39
    Activations Density 0.000%

    No Known Activations