© 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. 141873
    Prev
    Next
    INDEX
    Explanations

    silicone sealant, delicate possessions

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

    explains why or impacts

    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
    วั
    0.47
    รู้จัก
    0.46
    அ
    0.46
    pitched
    0.45
    ಂ
    0.43
    |}\
    0.42
    вЂ
    0.42
    னுடன்
    0.41
    ผู้
    0.40
    handedly
    0.40
    POSITIVE LOGITS
    𝐲
    0.50
    ارك
    0.49
     Flock
    0.46
    ENCIA
    0.46
     individ
    0.43
    Expense
    0.43
    линд
    0.43
    拉克
    0.42
    tk
    0.42
    法人
    0.42
    Activations Density 0.002%

    No Known Activations