© 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. 191018
    Prev
    Next
    INDEX
    Explanations

    additional stock, bonus on, merchandise

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

    objective measurements

    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
    üler
    0.49
     ativid
    0.47
    混
    0.46
    ανά
    0.45
    지가
    0.45
    র্জন
    0.44
    ⟢
    0.44
    drž
    0.44
     ऑगस्ट
    0.44
    ([],
    0.43
    POSITIVE LOGITS
     de
    0.47
     ofthe
    0.44
     relocate
    0.42
    </h2>
    0.41
     increasing
    0.40
    Sweep
    0.40
     fugit
    0.39
     tinta
    0.39
     Spin
    0.39
    ască
    0.39
    Activations Density 0.000%

    No Known Activations