© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    have used

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

    tree diagram components

    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
    搭载
    0.43
    仂
    0.43
    рованной
    0.42
    极致
    0.42
    ธอ
    0.42
     macaw
    0.42
    Vk
    0.42
    얹
    0.42
    भव
    0.41
     인한
    0.41
    POSITIVE LOGITS
     Checking
    0.47
     Drugs
    0.45
     Examining
    0.44
     Muslims
    0.44
     വൈദ്യ
    0.43
     Одна
    0.42
     Determining
    0.42
     Basically
    0.42
     Anybody
    0.41
     Після
    0.41
    Activations Density 0.000%

    No Known Activations