© 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. 255752
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ಇದೆ
    0.49
     সির
    0.48
    这是一个
    0.48
    内
    0.46
     Европа
    0.46
    使用的是
    0.45
     đó
    0.44
     ገን
    0.44
     বেশিরভাগ
    0.44
    噢
    0.43
    POSITIVE LOGITS
     hypothetical
    0.44
     hypotheses
    0.44
     prompting
    0.43
     hypothes
    0.43
     architectural
    0.42
     encom
    0.42
     rehabilit
    0.42
     ventilators
    0.42
     covari
    0.41
     hydroph
    0.40
    Activations Density 0.002%

    No Known Activations