© 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. 122364
    Prev
    Next
    INDEX
    Explanations

    food ingredients and storage

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

    technical definitions and descriptions

    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
    悖
    0.44
     preparedness
    0.43
    而
    0.43
    場合
    0.42
     Werbung
    0.41
    </sup>
    0.40
    事を
    0.39
    比較的
    0.39
     服
    0.39
     :=
    0.39
    POSITIVE LOGITS
     colourful
    0.48
     headspace
    0.47
     uczni
    0.44
     photocurrent
    0.44
     प्रतियोग
    0.43
    madı
    0.43
    rared
    0.43
    ۀ
    0.43
    degenerative
    0.42
    光谱
    0.42
    Activations Density 0.000%

    No Known Activations