© 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. 1355
    Prev
    Next
    INDEX
    Explanations

    ParkMobile can

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

    demeter & phishing

    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
    ل
    0.21
    D
    0.20
    yatiti
    0.19
    L
    0.19
    M
    0.19
     سی
    0.19
     ディ
    0.18
     ഡ
    0.18
     ولی
    0.18
    โ
    0.18
    POSITIVE LOGITS
    的故事
    0.20
    UILLER
    0.18
    ®,
    0.17
    故事
    0.16
     REACTORS
    0.16
    绶
    0.16
     disruptive
    0.15
     pungent
    0.15
    쨩
    0.15
    Antaeotricha
    0.15
    Activations Density 1.864%

    No Known Activations